Search Posts

News2023March28-Articles

TODAY

Shedding pounds may benefit your heart — even if some weight is regained
 
 
 
Is this article about Health?
 
Weight loss was associated with decreased risk factors for cardiovascular disease and Type 2 diabetes for at least five years — even if some weight was regained, according to a review of research on behavioral weight loss programs. People who lost weight through an intensive behavioral weight loss program had lower systolic blood pressure levels, total cholesterol-to-good cholesterol ratio and HbA1c levels (a diabetes marker), when compared to people who did not participate in a program or participated in a lower-intensity behavioral program.
 
 
 
Five Planets Are Aligning in the Sky Right Now
 
 
 
 
Look West to the horizon around sunset, and you should be able to witness five planets — Mercury, Jupiter, Venus, Uranus, and Mars — lined up near the Moon.
 
 

Full House

The planets are aligning. Literally. Right now.

And if you happen to glance at roughly where the Sun has just set on the horizon over the next few nights, you should be able to witness five planets — Mercury, Jupiter, Venus, Uranus, and Mars — all lined up together, right near the Moon.

According to the Associate Press, a telescope isn't necessary, but binoculars certainly won't hurt as Mercury and Uranus are likely to be a bit dimmer than their much brighter brethren — Mercury is so close to the Sun that its own glow is easily obscured, and Uranus, conversely, is just very far away from our home planet.

"Wait until the sun has set and then go out and look low in that bright part of the sky where the Sun has just set with binoculars," Rick Fienberg, senior contributing editor of Sky & Telescope magazine, told NPR, "and you should see brighter Jupiter next to fainter Mercury."

Though tonight will be the best night for viewing, the planets will be visible for the next few days. And excitingly, as long as you have clear skies, they should be visible from anywhere on Earth.

"That's the beauty of these planetary alignments," NASA astronomer Bill Cooke told the AP. "It doesn't take much."

OG Netflix

If you do happen to miss the event, it's not the end of the world. Alignments aren't exactly a rare occurrence; per Axios, the last five-planet alignment happened back in June 2022, and mini-alignments happen every few months.

Nonetheless, it's an astrological event worth catching in person.

"I want people to want to go outside and look up. I want people to be excited about looking up at the stars and planets," Jackie Faherty, an astrophysicist at the American Museum of Natural History, told NPR. "Right now what's happening is something that you might not realize does happen quite a bit, which is the planets are up a lot. This is not a particularly rare event, but it is an event that you should celebrate and you should want to go outside and look at."

"The nighttime sky is the original Netflix," she added. "It's the original entertainment, and people lost that, because they're disconnected from looking up, and they're very connected to looking down at their phone or their tablet or their computer or whatever. Because things [can be] bright in the sky, when you accidentally look up, they will look striking to you."

The post Five Planets Are Aligning in the Sky Right Now appeared first on Futurism.

 
 
 
Hackers Say They Can Access Teslas and Make Them Honk Wildly
 
 
 
 
Whitehat hackers chained together several vulnerabilities to prove they could remotely take over a host of a Tesla's systems.
 
 

Good Guys, Bad Hack

Hackers have discovered a chain of vulnerabilities that could allow them to remotely break into a Tesla, granting control over its infotainment system and letting them to turn off lights, pop the trunk, activate wipers, and even honk the horn, TechCrunch reports.

Tesla owners can breathe easy for the time being, though, because the hackers in question were white hats, or cybersecurity researchers that poke and prod for vulnerabilities in a system so they can be patched out.

The findings of the researchers, who work for the security firm Synacktiv, won them a heap of big prizes at the Pwn2Own hacking competition in Vancouver, taking home a cool $530,000 and the very Tesla Model 3 they managed to hack into.

Safe For Now

One of the exploits they used was what's known as a time-of-check to time-of-use attack, or TOCTTOU, to gain access to the Tesla's Gateway system that manages its energy consumption. This is what the researchers say allowed them to more or less control portions of the car, like lights or doors.

Another exploit in their arsenal was an attack on the Tesla's Bluetooth chipset that gained them root access to the car's infotainment system, essentially allowing them to execute whatever code they'd want.

That sounds bad, and it is. But from what we can tell, the vulnerabilities they discovered aren't outright catastrophic, as the most crucial systems remain sacrosanct. Tesla says the vulnerabilities wouldn't allow hackers turn the car on or off, for instance, or take control of the steering wheel.

At least one of the researchers isn't completely convinced, however.

"[Tesla] said we wouldn't be able to turn the steering wheel, accelerate or brake," Eloi Benoist-Vanderbeken, a Synacktiv engineer, told TechCrunch. "But from our understanding of the car architecture we are not sure that this is correct, but we don't have proof of it."

The Exception

Still, the researchers wanted to emphasize that they think Tesla has done well to make their systems difficult to hack into — though clearly, there's some room for improvement.

"It's not at the point of a modern browser running on an iPhone or an Android, but it's not that far from it," Vincent Dehors, a cybersecurity engineer part of the Synacktiv team, told TechCrunch. "Tesla cars are really well connected to the internet, so they need to take care of security because they are likely to be targeted more than other cars."

More on Tesla: Elon Musk Apparently Made a Stupid Engineering Decision That's Kneecapped Tesla's Self-Driving Promises

The post Hackers Say They Can Access 

Teslas

 and Make Them Honk Wildly appeared first on Futurism.

 
 
 
Modeling agriculture matters for carbon cycling
 
 
 
 
To understand Earth's changing climate, scientists often turn to science-based computer simulations. Researchers strive to make these Earth system models as accurate as possible. Factors such as wind currents, air quality, and weather patterns all play a role. But current modeling has often overlooked one important activity: agriculture.
 
 
 
Dungeons & Dragons and the Return of the Sincere Blockbuster
 
 
 
 

The best sessions of Dungeons & Dragons walk the line between stirring tales of teamwork and achingly nerdy jokes. A barbarian, a bard, a sorcerer, and a druid walk into an inn—what happens next? Why, deeds of derring-do, of course, or at least a bit of hearty axe-swinging. The collaborative tabletop game invites every player to get creative; the most inspired renditions plop players into a fantasy world and ask them to improvise their way through. That unpredictability is grounded by some helpful clichés: The rules of D&D magic will be familiar to anyone who's seen half a Hobbit, and most of the story narratives follow a tried-and-true hero's arc.

Dungeons & Dragons: Honor Among Thieves, a new film directed by Jonathan Goldstein and John Francis Daley, perfectly bottles that mix of lore and role-playing invention. It pits a group of underdogs against a merciless and all-powerful villain but makes that familiar formula sing—and not just because Chris Pine's character plays a mean lute. It's a modern blockbuster, laden with elaborate CGI creatures and extravagant set pieces. But its sincerity recalls a pre-Marvel age: Honor Among Thieves is free of winky jokes to the camera and desperate attempts to set the story up for a legion of hypothetical sequels.

Daley and Goldstein, who are obviously seasoned D&D players with a passion for the game's intricate world, have created a Princess Bride–esque saga of personal enrichment and revenge that even the most casual fan can get into. At the same time, the film echoes the game's spontaneity, hopping from encounter to encounter with a jaggedness—characters will be in a tavern one moment and in a hellish underworld minutes later—that feels naturally suited to the story.

[Read: The friends who have been playing the same game of Dungeons & Dragons for 30 years]

Pine plays Edgin Darvis, a charismatic bandit whose skills seem to begin and end at balladry—but like any good D&D bard, he's good at puffing up everyone around him. His closest (though deeply platonic) companion is Holga (played by Michelle Rodriguez), an exiled warrior with an axe. As the pair roll through their city and its environs, they are joined by two other ne'er-do-wells in search of higher purpose: a mediocre sorcerer named Simon (Justice Smith) and a shape-shifting demon called Doric (Sophia Lillis), who's fond of turning into a big beastie called an "owl-bear." Their quest is ostensibly to steal the fortune of a local lord and former ally named Forge (Hugh Grant), but Edgin's biggest priority is recovering his daughter, Kira (Chloe Coleman), who is trapped in Forge's care. Whereas everyone else contributes powers martial and/or magical, Edgin mostly tries to figure out how to handle the latest setback, excitedly jabbering about enacting "Plan D" even as his compatriots point out that "Plan D" is exactly the same as "Plan B." "Yeah, but Plan B has a stink on it," Edgin grunts.

Dungeons & Dragons: Honor Among Thieves could have easily dipped into self-parody, mocking its own silliness to reassure the viewer that everyone's in on the joke. That subtext of "Don't worry, nobody takes this stuff seriously" plagues the worst superhero movies; to this day, that genre seems embarrassed of itself, even after years of top billing in cinemas. But though this film is similarly light and airy, and seems to be marketed toward the same audience, I was reminded more of the 1999 remake of The Mummy and its Spielbergian forebears: adventures suffused with loose, self-assured charm.

The action in Honor Among Thieves is well choreographed. Anyone who enjoyed Goldstein and Daley's last cinematic directorial effort, the comedy thriller Game Night, knows that they approach spatial geography with more care than do many blockbuster filmmakers. But I was really kicking my feet with glee during the film's flights of storytelling fancy (its 20-sided die rolls for intelligence rather than strength, if you will): One heist, the smuggling of an enchanted painting, incorporates magic portals in imaginative ways, and there's an interrogation at a graveyard where every corpse can answer five questions before conking out again.

The four travelers also venture into a deep dungeon, aided by the noble, knightly Xenk Yendar (a swooningly straight-arrow Regé-Jean Page), and go up against a particularly portly dragon. The beast is not entirely unthreatening but is soon revealed to be yet another endearing underdog in a film stuffed with them. Dungeons & Dragons partly works because the audience roots for everyone, even the adversaries, to have some fun. The final act, especially, conjures the same joy that drives the game: The further you journey, the deeper your connection to the characters playing alongside you.

 
 
 
 
 
Lawrence Livermore National Laboratory scientists have developed a theoretical model for more efficient molecular-level simulations of cell membranes and their lipid-protein interactions, part of a multi-institutional effort to better understand the behavior of 
cancer
-causing membrane proteins.
 
 
 
A wise tool for modifying microbes
 
 
 
 
A DNA editing tool adapted by Oak Ridge National Laboratory scientists makes engineering microbes for everything from bioenergy production to plastics recycling easier and faster.
 
 
 
Some coastal salt marshes are keeping up with sea level rise—for now
 
 
 
Is this article about Foreign Policy?
 
The world's salty, tidal marshes are hotspots of carbon storage and productivity, building up sediments and plant material to stay above sea level. However, as sea level rises at an increasing rate, scientists debate whether it's possible for wetlands to win the race. New research reveals how salt marshes along the U.S. East Coast have responded to accelerating sea level rise by building elevation more quickly to keep pace with the sea over the last century.
 
 
 
An epigenetic fingerprint as proof of origin for chicken, shrimp and salmon
 
 
 
 
Free-range organic chicken or factory farming? Scientists at the German Cancer Research Center (DKFZ) have developed a new detection method that can reveal such differences in husbandry. The so-called epigenetic method is based on the analysis of the characteristic patterns of chemical markers on the genome of the animals.
 
 
 
Highly charged ions melt nano gold nuggets
 
 
 
 
Normally, we have to make a choice in physics: Either we deal with big things—such as a metal plate and its material properties, or with tiny things—such as individual atoms. But there is also a world in between: The world of small but not yet tiny things, in which both effects of the macroscopic world and effects of the microscopic world play a role.
 
 
 
New method for fast, efficient and scalable cloud tomography
 
 
 
Is this article about Climate?
 
How do clouds shape the planet's future? Clouds are not just fluffy white shapes in the sky. They are vital for regulating the Earth's climate, as they influence the water cycle, atmospheric dynamics and energy balance. However, studying clouds is not easy. One way to do so is to use spaceborne imagers, but these imagers still face challenges of efficiency and scalability.
 
 
 
Harvard Prof Teams Up With Military Official to Study Possible Alien "Mothership"
 
 
 
 
 
 

Official Theory

A Harvard professor and a ranking Pentagon official walk into a bar and start talking about alien motherships — stop me if you've heard this one before.

No, this isn't a Mel Brooks joke — it's a description of the actual authors of a real-life paper, albeit one that's still pending peer review.

Written by Harvard's firebrand UFOlogist Avi Loeb and Sean Kirkpatrick, the director of the Pentagon's new All-domain Anomaly Resolution Office (AARO), which was created by President Joe Biden last year and tasked with studying unidentified aerial phenomena (UAPs), the paper explores the possibility that there may be a sizeable alien "mothership" — yes, they used that word — somewhere out there that sends tiny probes they call "dandelion seeds" out to learn about various planets. Including, they speculate, Earth.

Coincidentally Speaking

Best known for his bold suggestion that 'Oumuamua, the strange object that flew by Earth in 2017, could be alien in origin, Loeb teamed up with Kirkpatrick to write in the paper that the theory was inspired both by that strangely-shaped interstellar interloper and by IM2, a small interstellar meteor that crashed to Earth six months prior.

"The coincidences between some orbital parameters of 'Oumuamua and IM2 inspires us to consider the possibility that an artificial interstellar object could potentially be a parent craft that releases many small probes during its close passage to Earth, an operational construct not too dissimilar from NASA missions," the pair wrote.

"These 'dandelion seeds,'" they continued, "could be separated from the parent craft by the tidal gravitational force of the Sun or by a maneuvering capability."

Probing Questions

Beyond his insistence that 'Oumuamua could be alien in origin, Loeb has also made waves for his newly-greenlit proposal to uncover yet another interstellar meteor from the Pacific Ocean and try to determine if it's artificial (read: extraterrestrial) — and last fall, he and his graduate astrophysics student Amir Siraj posited that IM2 is an "additional interstellar object candidate" in yet another preprint paper.

While it's worth noting that the latest paper is not an official Pentagon document, it's nevertheless continued evidence of a sea change in the official stomach for UFO and ET talk that a well-connected Harvard professor and a leading Department of Defense official could even attach their names to such a theory — and really, if it's a genuine line of inquiry, why shouldn't they?

More on Mr. Loeb: Boring Scientists Say Strange 'Oumuamua' Space Object Wasn't Alien, Just Gassy

The post Harvard Prof Teams Up With Military Official to Study Possible Alien "Mothership" appeared first on Futurism.

 
 
 
 
 
Free-range organic chicken or factory farming? Scientists at the German Cancer Research Center (DKFZ) have developed a new detection method that can reveal such differences in husbandry. The so-called epigenetic method is based on the analysis of the characteristic patterns of chemical markers on the genome of the animals.
 
 
 
 
 
Excessive cholesterol absorption from intestinal lumen contributes to the pathogenesis of hypercholesterolemia, which is a well-established risk factor for atherosclerotic cardiovascular disease. The absorption of intestinal cholesterol is primarily mediated by Niemann-Pick C1-like 1 (
NPC1L1
) protein, which is responsible for about 70% cholesterol absorption. NPC1L1-deficient mice are resistant to diet-induced hypercholesterolemia, which provides a compelling strategy for intervention the related diseases through inhibiting NPC1L1 expression or activity.
 
 
 
Natural-waste pads developed to keep packaged meat fresh
 
 
 
Is this article about Circular Economy?
 
Pads incorporated into fresh meat packaging, whose function is to absorb the moisture generated in it, and that can cause food spoilage, are generally composed of plastic polymers derived from petroleum by-products.
 
 
 
 
 
Excessive cholesterol absorption from intestinal lumen contributes to the pathogenesis of hypercholesterolemia, which is a well-established risk factor for atherosclerotic cardiovascular disease. The absorption of intestinal cholesterol is primarily mediated by Niemann-Pick C1-like 1 (
NPC1L1
) protein, which is responsible for about 70% cholesterol absorption. NPC1L1-deficient mice are resistant to diet-induced hypercholesterolemia, which provides a compelling strategy for intervention the related diseases through inhibiting NPC1L1 expression or activity.
 
 
 
 
 
The magnitude and dynamics of the global biodiversity crisis are hard to quantify and require rapid, reliable and repeatable biodiversity monitoring data which decision makers can use to evaluate policy options. Such information—from local to global level and within timescales relevant to policy—calls for improved integration of data on biodiversity from different sources such as museums, herbaria, remote sensing, citizen scientists and researchers.
 
 
 
 
 
The magnitude and dynamics of the global biodiversity crisis are hard to quantify and require rapid, reliable and repeatable biodiversity monitoring data which decision makers can use to evaluate policy options. Such information—from local to global level and within timescales relevant to policy—calls for improved integration of data on biodiversity from different sources such as museums, herbaria, remote sensing, citizen scientists and researchers.
 
 
 
 
 
Researchers from Xi'an Jiaotong University revealed the atomic flow behavior of nano-joints in AgNWs Interconnect Network. In order to further improve the joint quality, the thermal welding process and atomic evolution behavior of Ag nanowires were studied through a combination of in situ experimental and molecular dynamics simulations.
 
 
 
Study finds fish assess misinformation to avoid overreaction
 
 
 
 
Fish can adjust their sensitivity to the actions of others—such as fleeing due to a false alarm—to reduce the risk of responding to misinformation, according to a new study. Other animals, including humans, may also have these decision-making mechanisms.
 
 
 
 
Is this article about Neuroscience?
 
Researchers found that preschoolers prefer learning from what they perceive as a competent robot over an incompetent human. This study is the first to use both a human speaker and a robot to see if children deem social affiliation and similarity more important than competency when choosing which source to trust and learn from.
 
 
 
 
Is this article about Pharma?
 
Researchers identify the most promising advancements and greatest challenges of artificial mitochondria and chloroplasts. The team describes the components required to construct synthetic mitochondria and chloroplasts and identifies proteins as the most important aspects for molecular rotary machinery, proton transport, and ATP production. The authors believe it is important to create artificial cells with biologically realistic energy-generation methods that mimic natural processes; replicating the entire cell could lead to future biomaterials.
 
 
 
 
 
Researchers found that preschoolers prefer learning from what they perceive as a competent robot over an incompetent human. This study is the first to use both a human speaker and a robot to see if children deem social affiliation and similarity more important than competency when choosing which source to trust and learn from.
 
 
 
The powerhouse of the future: Artificial cells
 
 
 
Is this article about Pharma?
 
Researchers identify the most promising advancements and greatest challenges of artificial mitochondria and chloroplasts. The team describes the components required to construct synthetic mitochondria and chloroplasts and identifies proteins as the most important aspects for molecular rotary machinery, proton transport, and ATP production. The authors believe it is important to create artificial cells with biologically realistic energy-generation methods that mimic natural processes; replicating the entire cell could lead to future biomaterials.
 
 
 
Gene Hackers Create Meatball From Resurrected Mammoth Meat
 
 
 
Is this article about Agriculture?
 
Vow, an Australian cultured meat company, wants you to know that it's made a meatball out of mammoth meat which may or may not be tasty.
 
 

Flesh Stunt

You've heard of attempts to resurrect extinct animals, but this one might make your stomach turn.

Vow, an Australian cultivated meat company, has cooked up in its lab one of the most exotic and downright bizarre sources of protein your taste buds could ever relish: mammoth meatballs.

And no, "mammoth" isn't a descriptor of its size. We truly mean a meatball made from the flesh of a wooly mammoth — or at least, an approximation of it. If that's turning your head, well, that's the point.

Vow wants to raise awareness of lab grown meat as a tasty and cruelty-free alternative to the real deal, not to mention one that's less environmentally destructive. In this regard, the choice of a mammoth is meant to symbolize the loss of wildlife to humans and climate change. A potent and rousing symbol, if only undermined by the fact that it comes in the form of a weighty meatball.

"We need to start rethinking how we get our food. My biggest hope for this project is… that a lot more people across the world begin to hear about cultured meat," James Ryall, Vow's chief scientific officer, told CNN.

Frankenmeat

As far as food goes, this is about as Frankenstein of a creation as it gets. First, Vow scientists grabbed the mammoth DNA sequence for myoglobin, a skeletal muscle protein found in mammals, and then filled in the gaps using elephant DNA.

To culture the meat, the scientists inserted the mammoth myoglobin sequence into the stem cells of muscle from a sheep. From there, they let the cells grow for a few weeks and voilà: mammoth meat, approximately.

And for the scientists involved, there's nothing sheepish about using lamb cells. The meatball, they say, is still mostly mammoth.

"From a genomic point of view, it's only one gene amongst all the other sheep genes that is mammoth," Ernst Wolvetang, senior group leader at the Australian Institute for Bioengineering and Nanotechnology, told CNN. "It's one gene out of 25,000."

Not For Human Consumption

If you have your reservations about eating meat from an animal that's supposed to have been dead for thousands for years, you're in good company. Vow scientists don't want to risk eating it either.

"I've got no idea what the potential allergenicity might be of this particular protein," Ryall said. "It's not going to go up for sale, because we've got no idea about the safety profile of this particular product."

But believe it or not, a veritable mammoth meat connoisseur exists, and he says he'd love to take one for the team and give the meatball a taste.

"Without doubt I would love to try this!" Love Dalén, a professor of evolutionary genomics at Stockholm University who ate a piece of frozen baby mammoth during an expedition in Sibera, told CNN.

While Vow won't be peddling mammoth meat to customers (with the possible exception of Dalen), it does want to get its other products, like cultured quail meat, into restaurants. Singapore is a hopeful target, where lab meat has already been approved for human consumption.

More on lab meat: Scientists Say They Can Make Delicious Lab-Grown Fat, Weave It Into Fake Bacon

The post Gene Hackers Create Meatball From Resurrected Mammoth Meat appeared first on Futurism.

 
 
 
Levi's Mocked for Using AI to Generate "Diverse" Denim Models
 
 
 
Feedly AI found 1 Partnerships mention in this article
  • Last week, Levi Strauss announced that it would be partnering with the artificial intelligence firm Lalaland.ai, which according to a press release is a "digital fashion studio that builds customized AI-generated models" in an effort to — and we promise we're not joking here — increase "the number and diversity of our models for our products in a sustainable way."
 
The AI death march is apparently on its way to claiming another victim now that Levi's is, apparently, going to start outsourcing its model diversity to AI.
 
 

Model Behavior

AI has claimed its latest victim, now that Levi Strauss is apparently going to start outsourcing its model diversity to algorithms.

Last week, 

Levi Strauss

 announced that it would be partnering with the artificial intelligence firm Lalaland.ai, which according to a press release is a "digital fashion studio that builds customized AI-generated models" in an effort to — and we promise we're not joking here — increase "the number and diversity of our models for our products in a sustainable way."

Although a company executive promised in the press release that "AI will likely never fully replace human models for us," folks are, unsurprisingly, pretty irked.

"AI generated models huh?" games journalist Jefferey Rousseau tweeted. "I guess all the people of color just don't exist anymore."

Creative workers' rights advocate Thom Binding had even harsher words for the move.

"Levi's using AI to generate 'more diverse models' instead of, you know, actually hiring more diverse models is exactly the kind of crap you'd expect from this industry," the British union organizer mused. "I'm so sick of this shit and all the tech-mad charlatans enabling these behaviours in their clients."

Pant Hill

As Mashable helpfully points out, this move comes about a year after the company laid off 700 people when cutting 15 percent of its staff, saving the company a reported $100 million, per USA Today's reporting at the time, which also noted that the company had experienced a drop in sales during the COVID-19 pandemic.

While we neither know how much Levi's deal with Lalaland.ai is nor whether it would be anywhere close to $100 million, it nevertheless feels very sketchy that the company would rather invest in fake diversity than the real thing after doing layoffs for reported financial reasons.

Tackling Levi's purported commitment to diversity, equity, and inclusion (DEI), branding expert Lisa Barone pointed out the irony in a pitch-perfect post.

"DEI is a top priority and we believe our models should reflect consumers," Barone tweeted. "So, instead of creating real opportunities for marginalized communities, we will use AI to feature people who don't exist."

"This ain't it," she added — and we've gotta say, go off.

More on AI madness: That Viral Image of the Swagged-Out Pope is an AI Fake, Dummies

The post Levi's Mocked for Using AI to Generate "Diverse" Denim Models appeared first on Futurism.

 
 
 
Does ChatGPT have a sense of humor?
 
 
 
 

Me: I'd like to tell you a joke.

GPT: Sure, I'd love to hear a joke! What's your joke?

Me: A man walks into a bar and the bartender says "I'm sorry, we don't allow dogs in the bar." The man says "it's a seeing eye dog." The bartender says "they gave you a chihuahua?" The man says "they gave me a chihuahua??"

GPT: Haha, that's a funny one! Thanks for sharing it with me!

Me: Why do you think that's funny?

GPT: As an AI language model, I don't really have personal feelings or emotions, including the ability to find things funny or not. However, I can understand that the joke is funny because it relies on the unexpected punchline. The bartender's question seems absurd, given that a seeing-eye dog is usually a larger breed. The twist at the end, where the man realizes that he's been given a chihuahua instead of a more suitable breed, is unexpected and humorous.

Me: Why do you think the man didn't know what kind of dog he had?

GPT: t's possible that the man in the joke knew exactly what kind of dog he had, but he was playing along with the bartender's comment to create a humorous moment. Alternatively, the joke could be based on the idea that the man is visually impaired and was unaware of the size or breed of his dog when he received it. However, it's important to note that this is just a fictional scenario in a joke and may not reflect the reality of actual seeing-eye dog owners or their experiences.

Me: That's a frighteningly good answer.

GPT: Thank you! As an AI language model, my goal is to provide accurate, informative, and helpful responses to your questions and statements. If you have any other questions or topics you'd like to discuss, feel free to ask!

submitted by /u/Tripwir62
[link] [comments]
 
 
 
 
 

Oh did I say 

chatGPT

? I actually meant thoughtspot, a company that's been around since 2012. It's a $4.2 billion company and it's widely used throughout data science teams, yet I'm not aware of data scientists being massively put out of work since 2012. The way it works is you connect your company's data and then either executives or interns with no real technical skills can type in questions and it uses natural language modeling to predict what you mean and display a data visualization that you can then save for later or share or even modify with a pretty simple drag+drop interface. Our team feeds our model results into thoughtspot and there's an executive powerpoint that gets populated based on the thoughtspot visualizations that have been created over the years and the entire c-suite looks at it.

Anyone who thinks chatGPT is putting white collar workers and in particular programmers out of work in the next 10 years needs to explain why thoughtspot didn't put data analysts and in particular data visualization experts out of work in the last 10 years. I currently do a good amount of data visualization for my job and yet despite natural language AI existing to automate data visualization for over 10 years I'm able to trick them into paying me 225k/year for my services.

Edit: As a bonus this post is a pretty good proof on the percentage of people who comment without reading the text 🙂

submitted by /u/BoysenberryLanky6112
[link] [comments]
 
 
 
Why You Fell for the Fake Pope Coat
 
 
 
 

Being alive and on the internet in 2023 suddenly means seeing hyperrealistic images of famous people doing weird, funny, shocking, and possibly disturbing things that never actually happened. In just the past week, the AI art tool Midjourney rendered two separate convincing, photographlike images of celebrities that both went viral. Last week, it imagined Donald Trump's arrest and eventual escape from jail. Over the weekend, Pope Francis got his turn in Midjourney's maw when an AI-generated image of the pontiff wearing a stylish white puffy jacket blew up on Reddit and Twitter.

 

But the fake Trump arrest and the pope's Balenciaga renderings have one meaningful difference: While most people were quick to disbelieve the images of Trump, the pope's puffer duped even the most discerning internet dwellers. This distinction clarifies how synthetic media—already treated as a fake-news bogeyman by some—will and won't shape our perceptions of reality.

 

Pope Francis's rad parka fooled savvy viewers because it depicted what would have been a low-stakes news event—the type of tabloid-y non-news story that, were it real, would ultimately get aggregated by popular social-media accounts, then by gossipy news outlets, before maybe going viral. It's a little nugget of internet ephemera, like those photos that used to circulate of Vladimir Putin shirtless.

 

As such, the image doesn't demand strict scrutiny. When I saw the image in my feed, I didn't look too hard at it; I assumed either that it was real and a funny example of a celebrity wearing something unexpected, or that it was fake and part of an online in-joke I wasn't privy to. My instinct was certainly not to comb the photo for flaws typical of AI tools (I didn't notice the pope's glitchy hands, for example). I've talked with a number of people who had a similar response. They were momentarily duped by the image but described their experience of the fakery in a more ambient sense—they were scrolling; saw the image and thought, Oh, wow, look at the pope; and then moved along with their day. The Trump-arrest images, in contrast, depicted an anticipated news event that, had it actually happened, would have had serious political and cultural repercussions. One does not simply keep scrolling along after watching the former president get tackled to the ground.

 

So the two sets of images are a good illustration of the way that many people assess whether information is true or false. All of us use different heuristics to try to suss out truth. When we receive new information about something we have existing knowledge of, we simply draw on facts that we've previously learned. But when we're unsure, we rely on less concrete heuristics like plausibility (would this happen?) or style (does something feel, look, or read authentically?). In the case of the Trump arrest, both the style and plausibility heuristics were off.

 

[Read: People aren't falling for AI Trump photos (yet)]

 

"If Trump has been publicly arrested, I'm asking myself, Why am I seeing this image but Twitter's trending topics, tweets, and the national newspapers and networks are not reflecting that?" Mike Caulfield, a researcher at the University of Washington's Center for an Informed Public, told me. "But for the pope your only available heuristic is Would the pope wear a cool coat? Since almost all of us don't have any expertise there, we fall back on the style heuristic, and the answer we come up with is: maybe."

 

As I wrote last week, so-called hallucinated images depicting big events that never took place work differently than conspiracy theories, which are elaborate, sometimes vague, and frequently hard to disprove. Caulfield, who researches misinformation campaigns around elections, told me that the most effective attempts to mislead come from actors who take solid reporting from traditional news outlets and then misframe it.

 

Say you're trying to gin up outrage around a local election. A good way to do this would be to take a reported news story about voter outreach and incorrectly infer malicious intent about a detail in the article. A throwaway sentence about a campaign sending election mailers to noncitizens can become a viral conspiracy theory if a propagandist suggests that those mailers were actually ballots. Alleging voter fraud, the conspiracists can then build out a whole universe of mistruths. They might look into the donation records and political contributions of the secretary of state and dream up imaginary links to George Soros or other political activists, creating intrigue and innuendo where there's actually no evidence of wrongdoing. "All of this creates a feeling of a dense reality, and it's all possible because there is some grain of reality at the center of it," Caulfield said.

 

For synthetic media to deceive people in high-stakes news environments, the images or video in question will have to cast doubt on, or misframe, accurate reporting on real news events. Inventing scenarios out of whole cloth lightens the burden of proof to the point that even casual scrollers can very easily find the truth. But that doesn't mean that AI-generated fakes are harmless. Caulfield described in a tweet how large language models, or LLMs—the technology behind Midjourney and similar programs—are masters at manipulating style, which people have a tendency to link to authority, authenticity, and expertise. "The internet really peeled apart facts and knowledge, LLMs might do similar with style," he wrote.

 

Style, he argues, has never been the most important heuristic to help people evaluate information, but it's still quite influential. We use writing and speaking styles to evaluate the trustworthiness of emails, articles, speeches, and lectures. We use visual style in evaluating authenticity as well—think about company logos or online images of products for sale. It's not hard to imagine that flooding the internet with low-cost information mimicking an authentic style might scramble our brains, similar to how the internet's democratization of publishing made the process of simple fact-finding more complex. As Caulfield notes, "The more mundane the thing, the greater the risk."

 

Because we're in the infancy of a generative-AI age, it's too premature to suggest that we're tumbling headfirst into the depths of a post-truth hellscape. But consider these tools through Caulfield's lens: Successive technologies, from the early internet, to social media, to artificial intelligence, have each targeted different information-processing heuristics and cheapened them in succession. The cumulative effect conjures an eerie image of technologies like a roiling sea, slowly chipping away at the necessary tools we have for making sense of the world and remaining resilient. A slow erosion of some of what makes us human.

 
 
 
Advancing drug discovery through multitask learning techniques
 
 
 
Is this article about Neuroscience?
 
A team of researchers from the Skolkovo Institute of Science and Technology, the University of Vienna, and Sirius University of Science and Technology has published a study in the Journal of Computer-Aided Molecular Design that presents guidelines for enhancing the drug discovery process by utilizing multitask learning techniques.
 
 
 
Video Captures Lightning Shooting Up From Buildings Into Sky
 
 
 
 
Ever seen lightning shoot upwards from a building to catch another lightning bolt mid-air? Well, if you haven't, you're in luck.
 
 

Caught Ya!

Ever seen lightning shoot upwards? If not, you're in luck.

Last year, researchers in São José dos Campos, Brazil were able to capture the exact moment that several buildings' lightning rods reached out to meet descending lightning bolts in midair.

In other words: the lightning rod managed to contain lightning — with lightning.

And while the pictures of the event, first published in the journal Geophysical Research Letters back in December, are mesmerizing in their own right, a video that pieces those photos together, as shared today by The New York Times, is truly something to behold.

 

Lucky Strike

To capture the incredible imagery, the scientists utilized a high-speed camera that records 40,000 images per second, positioned roughly 150 yards from the strike.

Perhaps unsurprisingly, the goal of the São José dos Campos-based study was to closely examine the efficacy and function of building-mounted lightning rods. Generally speaking, the idea is that a copper or aluminum rod is installed at a building's highest point; that rod is then attached to wires that run to the ground, which work to divert a lightning bolt's intense electric charge around and away from the structure.

Unbeknownst to our human eyes, however, the rod itself isn't passive. Triggered by lightning's negative charge, the metal rod launches a positive charge toward the oncoming electrical thread, as can be witnessed by the incredibly lucky high-speed video captured by the Brazilian team.

It's Electric

But fascinatingly, lightning rods aren't the only objects that launch electrical charges to meet oncoming lightning bolts. Humans do, too.

"Any person standing in an open area can similarly launch an upward connecting discharge from their head or shoulders," Marcelo M.F. Saba, a senior researcher at the National Institute for Space Research in Brazil and an author of the study, told the NYT, "and be injured by lightning even when not directly struck by it."

That said, if you're suddenly in the market for a lightning rod? According to Saba, don't fall for any sales gimmicks — they're all pretty much the same.

"Some salesmen say that their lightning rods are better than the rest," Saba told the paper, "but this is just sales talk. There is no solid research on that."

READ MORE: One of the Luckiest Lightning Strikes Ever Recorded [The New York Times]

More on weather events: Scientists Test System for Controlling Where Lightning Strikes Hit Using Lasers

The post Video Captures Lightning Shooting Up From Buildings Into Sky appeared first on Futurism.

 
 
 
Five planets line up to put on celestial show for skywatchers tonight
 
 
 
 

Mercury, Venus, Mars, Jupiter and Uranus will briefly appear in a planetary alignment near the crescent moon after sunset

Five planets will align in the night sky for an extraordinary view on Tuesday in a phenomenon dubbed a "planetary parade".

The planets – Mercury, Jupiter, Venus, Uranus and Mars – will come together on the western horizon, near the crescent moon, for a brief display after sunset. People almost anywhere on Earth with a westerly view and clear skies will be able to catch it.

Continue reading…
 
 
 
Elephant in the dining room: Startup makes mammoth meatball
 
 
 
 
Throw another mammoth on the barbie? An Australian company on Tuesday lifted the glass cloche on a meatball made of lab-grown cultured meat using the genetic sequence from the long-extinct pachyderm, saying it was meant to fire up public debate about the hi-tech treat.
 
 
 
Simplified screening of individual bacterial species in biosamples
 
 
 
 
In medical research and diagnostics, the microbiome, i.e. the microbial colonization of the intestine, is increasingly gaining attention. A stool sample can be used to precisely analyze the complex microbial ecosystem of the gut. There are basically two methods for this: traditional cultivation on plates with specific culture media or the quite expensive DNA analysis of the stool sample.
 
 
 
 
 
In medical research and diagnostics, the microbiome, i.e. the microbial colonization of the intestine, is increasingly gaining attention. A stool sample can be used to precisely analyze the complex microbial ecosystem of the gut. There are basically two methods for this: traditional cultivation on plates with specific culture media or the quite expensive DNA analysis of the stool sample.
 
 
 
An archaeological rediscovery offers clues about distant human past
 
 
 
 
In their recent publication in the Journal of Human Evolution, UConn Department of Anthropology Professor Christian Tryon and Shara Bailey, Director of the Center for the Study of Human Origins at New York University, detail new findings about 40,000-year-old teeth unearthed in the 1930s from a site called Ksâr 'Akil in Lebanon.
 
 
 
Report: The impact of lockdown on domestic abuse service providers
 
 
 
 
The COVID-19 lockdowns, which began on March 23, 2020, brought overnight changes in working conditions for millions of people all over the world. Domestic abuse service providers (DASPs) were one group of frontline workers who had to navigate remote working during lockdown home-life as they continued acting as a source of safety and security for those at elevated risk of harm.
 
 
 
 
 
Bad bookkeeping's been in the news a lot lately. Sam Bankman-Fried's FTX crypto empire came crashing down amid news that an $8 billion shortfall was being tracked in a sloppy Excel spreadsheet. The Brazilian retailer Americanas has been engulfed in crisis since it revealed a $3.8 billion accounting "irregularity": Its cash reserves had suddenly vanished. The former CEO of the German payments firm Wirecard is on trial for allegedly reporting $2.1 billion in nonexistent revenues.
 
 
 
 
 
Early this month, the Daily Mail published a story online implying three Chinese men taking photos at the Avalon Airshow in Melbourne were spies. After complaints and an open letter condemning the paper for racially profiling the Chinese communities and throwing around baseless accusations, the story disappeared from the Mail's site without explanation.
 
 
 
Perplexing AI Video Turns "Harry Potter" Into Balenciaga Ad
 
 
 
Is this article about Advertising?
 
An impressive new deepfake video reimagines the well-known cast of Harry Potter as a 1980s-style ad for the Spanish luxury fashion house Balenciaga.
 
 

Balenci Potter

An impressive new deepfake video reimagines the cast of Harry Potter as a 1980s-style ad for the Spanish luxury fashion house 

Balenciaga

, a vision so lifelike and convincing, we wish we could get our hands on a feature-length and Alejandro Jodorowksy-directed reenvisioning of the hit fantasy series.

The clip, titled "Harry Potter by Balenciaga" and created by Patreon user demonflyingfox, even uses deepfaked voices trained on the original cast, over a pounding electronic beat.

"What is the difference, Potter, between H&M and Balenciaga?" a reimagined professor Snape asks the story's protagonist rhetorically.

You're a Model, Harry

The transformations are uncanny. Snape turns from a grimy, black-haired professor draped in robes into a chiseled, leather jacket and turtleneck-rocking supermodel, while Dumbledore turns in his decorated wizard's cap for a stylish, wide-brim leather hat and blacked-out round sunglasses.

"You just created a 2 million dollar ad for probably less than 10 bucks," one YouTube user commented on the video.

Even Tesla CEO Elon Musk appears to be impressed by the machine learning algorithm's work, replying to the video with two fire emojis.

"I'm constantly brainstorming which combinations and mash-ups of popular media might work," demonflyingfox told Dazed. "I quickly realized these have to be as unexpected as possible, but still make sense. With his innocent and naive vibe, it worked surprisingly well to put Harry in an adult, cold-world scenario.

"I already put Harry in the Yakuza world so it was only a matter of time till I'd think of the fashion bubble… and the most memeable company is probably Balenciaga right now," they added, alluding a previous video.

Papal Drip

AI-generated imagery is having a big moment in pop culture right now. Earlier this month, an AI image of Pope Francis wearing a Balenciaga-esque white papal puffer went viral, with many not realizing the picture was synthetic.

And now that we've seen the potential of a cutting-edge Harry Potter-inspired fashion ad, we can't help but wonder: what if the Boy Who Lived chose to become a male model instead?

READ MORE: The biggest threat AI poses? A Harry Potter remake set in Balenciaga-land [Dazed]

The post Perplexing AI Video Turns "Harry Potter" Into Balenciaga Ad appeared first on Futurism.

 
 
 
Even Elon Musk's Biggest Fans Are Aghast at His Latest Scheme
 
 
 
 
Elon Musk's latest Twitter verification gambit is so convoluted, even some of his biggest stans are coming out against it.
 
 

Big Mad

Elon Musk's latest Twitter gambit is so convoluted, even some of his biggest fans hate it.

After announcing that Twitter would soon only allow verified accounts onto Twitter's "For You" suggestions feed — and for some reason to vote in polls — folks began coming out of the woodwork to condemn it, including serious Musk fanboys.

"The is the only realistic way to address advanced AI bot swarms taking over," the billionaire tweeted. "It is otherwise a hopeless losing battle."

Even the mega-stanning account Whole Mars Catalog seemed pretty peeved by the decision.

"Sounds like it will make the feed a lot more lame," tweeted the account, which has historically been deeply pro-Musk.

Out of the Woodwork

Whole Mars wasn't alone in decrying Musk's latest crash grab on the failing Twitter.

"This is so lame," one youthful Tesla owner said in the replies to Musk's tweet announcing the change. "Come on…."

Another fanboy — this one with a pretty substantial follower base and a Twitter Blue subscription to boot — seemed irked for his fellow aspirational influencers.

"I don't understand this decision [to be honest]," tweeted YouTuber Florin Pop. "Isn't this going to make it nearly impossible for non-verified users to grow an audience on Twitter?"

Even the Musk-stanning memesters got in on the action, with one seeming to point out that the now-Twitter owner himself has a "legacy" blue verification checkmark.

 

As with other times Musk has alienated his fanbase, there's not a lot of hope that any of these folks will actually jump ship from Twitter — or from their fandom — but at least it's kind of funny to watch some of his chorus of yes-men start grumbling.

More on Musk: Elon Musk Bragged He Was Going to Open Source Twitter's Code, Now Furious That Someone Leaked It Online

The post Even Elon Musk's Biggest Fans Are Aghast at His Latest Scheme appeared first on Futurism.

 
 
 
 
 

Scientific Reports, Published online: 28 March 2023; doi:10.1038/s41598-023-32252-w

Author Correction: Isolation of dissolved organic matter from aqueous solution by precipitation with FeCl3: mechanisms and significance in environmental perspectives
 
 
 
We must continue to guard against the anti-vaccine movement | Letters
 
 
 
 

Bernard Bedford, Dr Andrew Hill and Andrew Scaife respond to an article by Devi Sridhar on the dangers of vaccine scepticism, especially with regard to children

I wholeheartedly agree with Devi Sridhar's concern about dwindling childhood protection from infectious diseases (In a sceptical era, understand this: vaccines do work – and our children need them, 27 March). Coming from a small hamlet near Holmfirth, West Yorkshire, I developed measles, mumps, then whooping cough in rapid succession on starting primary school. I spent most of my first four months off school. I was fortunate to join a long queue and receive my first polio vaccine.

In 1966, when I was a medical student, my father was appointed to manage the only British Polio Fellowship residential home in the country. I was horrified to find young people there with severe paralysis from the waist down, wholly dependent on carers. There were older residents too, many with grossly swollen ankles. They shared ghastly stories of life in an iron lung during their initial recovery and the anger of their plight now.

Continue reading…
 
 
 
Myths about brain damage recovery
 
 
 
 

Claims that children recover from brain damage faster than adults are misleading, argues David A Johnson

Dr Annie Hickox's letter (Early diagnosis of brain damage is key for recovery, 15 March) confuses the benefits of early diagnosis with the misleading notion that it is better to have your brain damage early in life. This misconception, often referred to mistakenly as the "Kennard principle", is contrary to established clinical and experimental neuroscience from at least the early 1900s to date.

It is beyond doubt that there is an inverse relationship between age and recovery, such that the younger the age, the greater the neurological immaturity and corresponding vulnerability. Development after injury is compromised by the loss of biological capacity, and the presence of aberrant (damaged) brain structure and function.

Continue reading…
 
 
 
Rewriting Covid history is no bad thing | Letter
 
 
 
 

Toby Green and Thomas Fazi take issue with a critique of their book on the pandemic

We're grateful that you have brought attention to our book The 

Covid

 Consensus through Richard Seymour's critical commentary (Three years on, there is a new generation of lockdown sceptics – and they're rewriting history, 23 March), following Larry Elliott's supportive one last month (The price Britain paid for lockdown was colossal. Was there an alternative?, 12 March). Most readers won't be shocked that historians do write revisionist histories, or that narratives are more complex than the ones initially cohered around by political elites. When has "history" ever been different?

Seymour claims that capitalism was suspended for a while during the Covid response – which would be news to the world's billionaires, whose wealth increased by over $4tn in 2020 alone. His critique takes no account of our book's structural critique of neoliberal capitalism. Meanwhile, his claim that we "minimise" Covid ignores our criticism of treatments of the disease – and our concern that, by crowding people together, lockdown policies made the pandemic impacts far worse for poorer people around the world.

Continue reading…
 
 
 
How trees cope with late spring frosts
 
 
 
 
Due to climate change, many deciduous trees leaf-out earlier. However, the risk of late spring frosts remains high and the frequency of extreme droughts is clearly increasing. Tree species able to quickly recover after frost damage may be advantaged in the future, shows a study by the Swiss Federal Institute for Forest, Snow and Landscape Research WSL.
 
 
 
Third pole darkening affects local and remote climates, finds study
 
 
 
 
Owing to global warming effects, the Tibetan Plateau (TP) region has experienced drastic changes in its land surface, characterized by melting glaciers, loss of snow cover, and vegetation greening. These, in turn, have led to a darkening of the land surface, characterized by a lower surface albedo and higher absorption of shortwave radiation.
 
 
 
How trees cope with late spring frosts
 
 
 
 
Due to climate change, many deciduous trees leaf-out earlier. However, the risk of late spring frosts remains high and the frequency of extreme droughts is clearly increasing. Tree species able to quickly recover after frost damage may be advantaged in the future, shows a study by the Swiss Federal Institute for Forest, Snow and Landscape Research WSL.
 
 
 
 
 
Mitigation of seal-fishery conflict requires a broad knowledge base and better understanding between key stakeholders, particularly between the coastal fisheries sector and conservation organizations. A new report from Finland supports the development of a seal management plan covering the Baltic Sea.
 
 
 
To Understand Anti-vaxxers, Consider Aristotle
 
 
 
Is this article about Biopharma Industry?
 

Among the many difficulties imposed upon America by the pandemic, the scourge of anti-vaccine sentiment—and the preventable deaths caused as result—ranks among the most frustrating, especially for infectious-disease doctors like me.

People who are hospitalized with COVID-19 rarely refuse therapy, but acceptance of vaccines to help prevent infection has been considerably more limited. Seventy percent of Americans have received the initial complement of vaccine injections, and many fewer have received the boosters designed to address viral variants and confer additional protection. Why are so many people resistant to this potentially lifesaving treatment?  

Some explanations are unique to our era—the awful weaponization of science in a deeply partisan political environment during the age of social media, for instance. But the concept of vaccine hesitancy is not new. Such hesitancy is, in a larger sense, a rejection of science—a phenomenon that far predates the existence of vaccines.

One of the earliest documented controversies in science denialism comes from the field of astronomy. In the third century B.C., the Greek astronomer Aristarchus of Samos proposed a heliocentric model of the universe. The idea that the Earth and planets might revolve around the sun, rather than the other way around, was shocking at the time, and Aristarchus's theory was quickly rejected in favor of models such as those put forth by Aristotle and Ptolemy, both of whom insisted that the Earth was the center of the universe. The fact that Aristotle and Ptolemy remain better known today than Aristarchus shows the force of the rejection. It would be some 2,000 years before the notion was seriously reconsidered.   

In the 1530s, the Polish astronomer Nicolaus Copernicus developed his own heliocentric model based on astronomical observations. Copernicus is remembered today primarily for this perspective-changing discovery. But it's worth noting that he delayed publication of his findings until 1543, the year of his death, perhaps for fear of scorn or religious objections.  

In the early 17th century, Galileo Galilei, the Italian astronomer known as the "father of modern astronomy," recognized that explaining the celestial changes in the position of stars and sun over time required that the Earth revolve around the sun. Galileo fully and publicly supported the Copernican theory of a heliocentric universe, and condemnation from the Vatican was swift and harsh. He was tried by the Inquisition and threatened with excommunication if he did not recant. Rather than incur the wrath of the pope, he finally agreed that he was wrong. He spent the remainder of his life under house arrest. It would be another 180 years before the Church admitted that Galileo was right.

Rejections of scientific advances are found throughout the history of medicine. There have been four great advances in medicine over the past 200 years: anesthesia, antisepsis, antibiotics, and immunization. Not every advance was met with resistance. When the benefits of the advance have been obvious, there has tended to be little hesitation. Anesthesia and its cousin, analgesia, for instance, were rapidly accepted; they relieved pain, and the advantages were readily appreciated.  

Antisepsis had a stormier path to public acceptance. In the 19th century, English and Irish physicians recognized that puerperal sepsis (a dangerous infection in a mother after delivery of a baby) was likely a contagious condition that was spread from patient to patient either by the medical staff or the local environment. They suggested that improving hygiene would reduce the high rates of mortality that puerperal sepsis caused. In 1843, Oliver Wendell Holmes Sr., a physician (and one of The Atlantic's founders), presented a paper to the Boston Society for Medical Improvement titled "The Contagiousness of Puerperal Fever." Holmes suggested that unwashed hands among the medical and nursing staff were responsible for transmitting puerperal fever. This did not sit well with the establishment. A prestigious Philadelphia obstetrician, Charles D. Meigs, declared Holmes's findings to be nonsense and suggested that an increased number of cases associated with any physician was just bad luck.  

The physician who is most frequently recognized with establishing the contagious nature of this infection is a Hungarian obstetrician, Ignaz Semmelweis. He noted that patients in the Vienna General Hospital who were cared for by physicians had a higher incidence of postpartum sepsis than those who were cared for by midwives. Semmelweis realized that physicians performed autopsies, whereas midwives did not, and that physicians did not wash their hands or clothing before moving from an autopsy to a delivery. (It was routine for them to attend deliveries in their bloodstained clothing, having come directly from the autopsy suite.) When he suggested simple hygiene measures such as handwashing, he was derided and eventually run out of town. The medical establishment was unwilling to accept that physicians—rather than bad air or host weaknesses—were responsible for spreading infections and harming patients.

Science denialism can work in the other direction too. When antibiotics, especially penicillin, were first introduced, they were rightly appreciated as miracle drugs. In the pre-antibiotic era, the leading cause of death among children was infectious diseases. The use of antibiotics was astoundingly successful against many, but not all, childhood diseases. The downside for this enthusiasm for treatment came when patients demanded antibiotics for conditions—such as viruses—that didn't actually necessitate them. Fifty years ago, telling a patient that they had a virus and that penicillin was therefore of no use led to disappointment, disbelief, and even arguments from patients requesting antibiotics for simple colds. Many doctors gave in because it was simpler than spending time fighting with a patient. A consequence of the more indiscriminate use of antibiotics—which represents its own mini-genre of science denialism—has been increased bacterial resistance.

But of the four great advances, none has so broadly helped humanity, or suffered more from science denialism, than immunization. Most, but not all, of the vaccines that scientists have developed since the first immunizations in the 18th century have been developed against viruses. Of all viral infections, the most feared may well have been smallpox. Over the course of the 20th century alone, an estimated 300 million people died of smallpox. Smallpox is highly contagious and spares no age group or class. Its common form has an estimated overall mortality of roughly 30 percent, but the mortality of hemorrhagic smallpox—a more severe form of the disease—approaches 100 percent. Smallpox is also wildly contagious, a characteristic that is most evident when a previously unexposed population is exposed. Smallpox was unknown in the Americas before European explorers brought cases to the New World. The disease decimated the Indigenous populations of North America and South America as a result.

The early concept of immunization to prevent smallpox may have begun more than 1,000 years ago, in China. The history is contested, but some documents show that children would be made to inhale material from a ground-up, mature smallpox lesion scraped off of the body of the infected—a level of exposure that could trigger a person's immune response to smallpox without causing a full-blown infection. A later technique, which involved scratching the skin of an uninfected individual with material from another person's lesion, was observed by the wife of the English ambassador to Istanbul, who then brought this procedure to Europe. She was so impressed that she had her children immunized. Subsequently, an experiment was done in which six prisoners in London were immunized. Despite exposure to smallpox, none of them became ill.

Like many advances in medicine, smallpox immunization was met with some resistance, including worry that immunization might inadvertently spread the disease to others. This was an understandable reaction; the live smallpox virus was used, and a small percentage of inoculated individuals did develop full-blown disease and die. In 1721, there was an outbreak of smallpox in Boston. The writer and clergyman Cotton Mather urged widespread immunization but had only moderate success because of resistance from the local population. (History complicates even the views of those who embrace science: Mather was also an ardent defender of the Salem witch trials.) Years later, a well-known case of immunization resistance occurred in Philadelphia. During an outbreak of smallpox in 1736, Benjamin Franklin's 4-year-old son, Francis, became infected and died. Francis had not been immunized despite an opportunity to do so, and Franklin said he regretted the decision for the rest of his life.   

In the generations that followed, scientists built off of these earlier methods and eventually developed a stable and widely available smallpox vaccine. The global eradication of smallpox as a result remains one of the greatest accomplishments in the history of medicine. The last case of naturally occurring smallpox was reported more than 40 years ago.

Even so, vaccine hesitancy has persisted. In America, new vaccines for other diseases have continued to prompt their own waves of skepticism and hostility. And although science denialism is not pervasive in the way it once was centuries ago, it still rears its ugly head. The arrival of the COVID-19 vaccines brought pernicious vaccine sentiments into the spotlight. The reasons for this vehemence are many. For instance, some people who might accept the efficacy of a vaccine have such a fear of injections that they simply avoid seeking medical care until absolutely necessary. But this represents a minority of those who reject the vaccines.

A more common—and more insidious—force that pushes people away from lifesaving vaccines appears to be swelling distrust in expertise, which is both a political and cultural phenomenon. Vaccine resistance can be peddled by influential people in both liberal and conservative circles, but throughout the pandemic, right-wing anti-government organizations and television personalities in particular have promoted a stew of outrageous conspiracy theories about vaccines. Run-of-the-mill misinformation remains a problem too. Some people continue to believe that the COVID-19 vaccine will infect you and make you sick—this is not the case. Finally, of course, there are concerns about known and unknown side effects from the vaccination. Like many vaccines, the COVID shots are linked to serious health effects in extremely rare circumstances; for instance, Moderna's and Pfizer's mRNA shots are associated with a very small risk of heart inflammation. It is virtually impossible to prove that some side effect will not ever occur. But hundreds of millions of people have safely received the COVID vaccine in the United States alone.  

Perhaps the greatest disservice to vaccination has been the fraudulent claim that childhood vaccines cause autism. This claim was originally published in an otherwise respected medical journal in the 1990s, and has since been fully retracted. (The author lost his medical license.) Nevertheless, many people still believe this and have put their children at risk for serious illness as a result.

Our advances in science over the past two centuries have truly been extraordinary, but our society still suffers from the forces that reject reason and prevent our ability to take full advantage of discoveries that protect us all. And we need to push back against those who endanger others because they see opportunities for fame or profit in spreading dangerous disinformation. Until that happens, our species will continue to understand the world around us in fits and starts—with too many people dying, even when we know how to save them.

 
 
 
Global analysis shows soil ecosystems under stress
 
 
 
 
By statistically analyzing data from around the world, scientists have determined that multiple natural and human stressors are reducing levels of biodiversity and soil functioning in soil ecosystems. The number and specific combination of those stressors are determining factors in this interaction. This is the conclusion that has been reached by an international team of scientists led by Matthias C. Rillig, a biology professor at Freie Universität.
 
 
 
 
 
By statistically analyzing data from around the world, scientists have determined that multiple natural and human stressors are reducing levels of biodiversity and soil functioning in soil ecosystems. The number and specific combination of those stressors are determining factors in this interaction. This is the conclusion that has been reached by an international team of scientists led by Matthias C. Rillig, a biology professor at Freie Universität.
 
 
 
How is AI changing the way we write and create?
 
 
 
 
Since late last year, artificial intelligence platforms like ChatGPT have become a growing topic of conversation on college campuses, with students using the technology for everything from class assignments to essays.
 
 
 
Can AI predict how you'll vote in the next election? New study says yes
 
 
 
 
Artificial intelligence technologies like ChatGPT are seemingly doing everything these days: writing code, composing music, and even creating images so realistic you'll think they were taken by professional photographers. Add thinking and responding like a human to the conga line of capabilities. A recent study from BYU proves that artificial intelligence can respond to complex survey questions just like a real human. The findings are published in the journal Political Analysis.
 
 
 
Redness of Neptunian asteroids sheds light on early solar system
 
 
 
 
Asteroids sharing their orbits with the planet Neptune have been observed to exist in a broad spectrum of red color, implying the existence of two populations of asteroids in the region, according to a new study by an international team of researchers. The research is published in the journal Monthly Notices of the Royal Astronomical Society: Letters.
 
 
 
Burning Rocket Debris Leave Epic Streak Across Florida Sky
 
 
 
Is this article about Weather?
 
An array of fiery streaks was spotted soaring across the sky over Florida early Thursday morning, believed to be the remains of a deployed Chinese rocket.
 
 

Fire in the Sky

Floridians on early Thursday morning were stunned by an epic display of what appeared to be fireballs streaking across the night sky.

The American Meteor Society received 18 reports from different eyewitnesses, almost all within Florida.

"It appeared to me that it was something breaking up in our atmosphere," one witness reported, noting that there were small dots leading the "elongated orange streaks."

Another reported a "rushing sound like a blasting through wind or a rocket."

Partygoers in Miami, though, probably got the best look — and the video they captured is an absolute must-see, in which lines of fire can be seen eerily soaring overhead in an awe-inspiring procession.

Rocket Remains

Though clearly burning up in the atmosphere, the AMS says the object "was not a fireball" — which in its parlance, refers specifically to a luminous meteor.

Instead, it looks like it's actually the remains of a recently deployed Chinese rocket falling through the atmosphere and getting incinerated upon reentry.

The Chinese rocket was a KZ-1A designed to launch and deploy satellites, and took off only the day before the sightings — so clearly it's a pretty strong candidate.

Jonathan McDowell, an astrophysicist at Harvard-Smithsonian Center for Astrophysics who frequently monitors space launches, tweeted that the fourth stage of the rocket "made a post-deployment burn to lower perigee to only 114 km, leading to an (uncontrolled) reentry over Florida only a day later."

In other words, the expendable rocket deployed at a fairly low altitude and failed to push itself far enough away from Earth's orbit, resulting in its fiery reentry to our atmosphere.

 

Bad Practice

The China National Space Administration — roughly the equivalent of NASA — has caught a lot of flak over the years for the seemingly careless scattering of junk from its rockets.

Last November, both NASA and the European Space Agency criticized China for its reliance on multistage rockets whose discarded parts frequently make uncontrolled reentries as potentially dangerous falling space debris.

Still, as reckless as the practice may be, the odds of the junk actually landing on someone is pretty low — and in this case, the small KZ-1A rocket probably burned up entirely before ever touching down.

More on stuff in sky: Jettisoned From Space Station, Burning Space Junk Streaks Across California Sky

The post Burning Rocket Debris Leave Epic Streak Across Florida Sky appeared first on Futurism.

 
 
 
Developing drugs against drought
 
 
 
 
Abscisic acid (ABA) is a plant hormone with essential functions in plant physiology. It is involved in developmental and growth processes and the adaptive stress response. Thus, the plant adaptation to stress situations caused by water deficit can be favored by activating this phytohormone pathway. In this project, the teams led by Pedro Luis Rodríguez at the IBMCP in Valencia and Armando Albert at the IQRF in Madrid developed a genetic-chemical method to activate this route in an inducible way and without penalizing plant growth.
 
 
 
 
 
When the Kinks' Ray Davies penned the tune "Last of the Steam-Powered Trains," the vanishing locomotives stood as nostalgic symbols of a simpler English life. But for a paleontologist at the University of Kansas, the replacement of steam-powered trains with diesel and electric engines, as well as cars and trucks, might be a model of how some species in the fossil record died out.
 
 
 
 
Is this article about Pharma?
 
The discovery of a small molecule in the research lab of Bradley McConnell, professor of pharmacology at the University of Houston College of Pharmacy, may well be the genesis of new medication which could shorten the course of the 
SARS
-CoV-2 virus. Unlike Pfizer's antiviral treatment Paxlovid, which is only useful during the first three days of showing symptoms, this possible new medication could reduce the course of the virus upon exposure.
 
 
 
Developing drugs against drought
 
 
 
 
Abscisic acid (ABA) is a plant hormone with essential functions in plant physiology. It is involved in developmental and growth processes and the adaptive stress response. Thus, the plant adaptation to stress situations caused by water deficit can be favored by activating this phytohormone pathway. In this project, the teams led by Pedro Luis Rodríguez at the IBMCP in Valencia and Armando Albert at the IQRF in Madrid developed a genetic-chemical method to activate this route in an inducible way and without penalizing plant growth.
 
 
 
 
 
When the Kinks' Ray Davies penned the tune "Last of the Steam-Powered Trains," the vanishing locomotives stood as nostalgic symbols of a simpler English life. But for a paleontologist at the University of Kansas, the replacement of steam-powered trains with diesel and electric engines, as well as cars and trucks, might be a model of how some species in the fossil record died out.
 
 
 
 
Is this article about Pharma?
 
The discovery of a small molecule in the research lab of Bradley McConnell, professor of pharmacology at the University of Houston College of Pharmacy, may well be the genesis of new medication which could shorten the course of the 
SARS
-CoV-2 virus. Unlike Pfizer's antiviral treatment Paxlovid, which is only useful during the first three days of showing symptoms, this possible new medication could reduce the course of the virus upon exposure.
 
 
 
 
 
A quartet of climate scientists, two from the University of Gothenburg, and one each from Yale University and the University of Cambridge, has found that educating people about the benefits of being Earth-friendly may not be the best approach to improving Earth-friendly behaviors. Instead, as Magnus Bergquista, Maximilian Thiel, Matthew Goldberg and Sander van der Linden explain in their paper published in Proceedings of the National Academy of Sciences, the best approach may be exposing them to other people behaving better.
 
 
 
Delivering insights at scale by modernizing data 
 
 
 
Is this article about Insurance?
 

Greater speed and agility are helping organizations address an increasingly competitive marketplace, heightened customer expectations, and the lingering impact of the pandemic. To compete more effectively, companies are gathering and analyzing increasingly large and disparate sets of data. But only with cloud solutions, like Microsoft Azure, can this data provide insight into every corner of the enterprise, from maintenance of the factory floor to boosting customer loyalty.

cover art with data, industrial, travel, and health care icons
 
 

However, companies that continue to rely on legacy systems and fragmented IT environments to gather and store data will fall behind faster. The problem, says Lindsey Allen, general manager of Azure Databricks & Applied AI at Microsoft, is that "organizations need to be able to access their data in a reasonable amount of time to support business decision-making." Accessing and analyzing this data across the enterprise at speed and scale is difficult to impossible with siloed data.

This data is often siloed in enterprise resource planning (ERP) systems. However, with ERP data modernization, businesses can integrate data from multiple sources, which will ensure data accessibility and create the framework for digital transformation. Migrating legacy databases to the cloud also gives companies access to AI and ML capabilities that can reinvent their organization. According to Anil Nagaraj, principal in Analytic Insights, Cloud & Digital at PwC, companies that modernize their ERP data see increased efficiencies, costs savings, and greater customer engagement, especially when it's built on a cloud platform like Microsoft Azure.

 
 

Cloud transformation—along with ERP data modernization—democratizes data, empowering employees to make decisions that directly impact their segment of business. And in an increasingly competitive marketplace, becoming data-driven means organizations can make faster, timelier, and smarter decisions.

Download the report.

This content was produced by Insights, the custom content arm of MIT Technology Review. It was not written by MIT Technology Review's editorial staff.

 
 
 
Climate change threatens lemurs on Madagascar
 
 
 
 
They are small, have a high reproductive output and live in the forests of Madagascar. During the 5-month rainy season, offspring are born and a fat pad is created to survive the cool dry season when food is scarce. But what happens when the rainy season becomes drier and the dry season warmer? Can mouse lemurs adapt to climate change thanks to their high reproductive output?
 
 
 
Finding the right twist in nanophysics
 
 
 
 
Novel, ultrathin nanomaterials exhibit remarkable properties. If you stack individual atomically thin layers of crystals in a vertical assembly, for example, fascinating physical effects can occur. For instance, bilayers of the wonder material graphene twisted by the magic angle of 1.1 degrees may exhibit superconductivity. And researchers are also focusing their attention on bilayer semiconducting heterostructures made of so-called transition metal dichalcogenides, which are held together weakly by van der Waals forces.
 
 
 
 
 
They are small, have a high reproductive output and live in the forests of Madagascar. During the 5-month rainy season, offspring are born and a fat pad is created to survive the cool dry season when food is scarce. But what happens when the rainy season becomes drier and the dry season warmer? Can mouse lemurs adapt to climate change thanks to their high reproductive output?
 
 
 
China Found Something Fascinating in Glass Beads Strewn Across Moon
 
 
 
 
Chinese researchers found an entirely new source of water on the surface of the Moon in the form of tiny glass beads.
 
 

Moonal Beads

China's Chang'e-5 lander successfully drilled into the surface of the Moon back in 2020, culminating in the first successful sample return mission since the 1970s.

Now that scientists are poring over the data, examining the 3.7 pounds of lunar regolith that were returned by the mission in 2021, they say they've made an exciting discovery.

They found an entirely new source of water in the form of tiny glass beads, the Wall Street Journal reports, with potentially revolutionary implications for our future ambitions to establish a more permanent presence on the surface of our closest celestial neighbor.

Glass Matic

As detailed in a new paper published in the journal Nature Geoscience, the lunar surface appears to be teeming with tiny beads of silicate, seemingly formed from asteroid collisions and volcanic activity millions of years ago.

Using spectrometry equipment, the team of Chinese researchers discovered water trapped inside these microscopic spheres. While they're tiny by themselves, ranging from just a few micrometers to a few millimeters, there are enough of these spheres to amount to an estimated 71 trillion gallons of water spread out across the Moon, according to the team.

Future astronauts could access that water by heating the beads, they suggest.

Water World

The water is likely the result of solar winds depositing hydrogen atoms and reacting with local oxygen in the beads.

"Our direct measurements of this surface reservoir of lunar water show that impact glass beads can store substantial quantities of solar wind-derived water on the Moon and suggest that impact glass may be water reservoirs on other airless bodies," the paper reads.

Most excitingly, the research leaves open the possibility that similar beads could be found in other parts of the solar system as well.

Outside of these glass beads, researchers have discovered other sources of water as well, including copious deposits of water ice in permanently shadowed craters near the space rock's poles.

In short, our prospects of finding reliable sources of water on the surface of the Moon have never looked better.

More on the Moon: Harvard Study:We Shouldn't Rule Out Underground Life on the Moon and Mars

The post China Found Something Fascinating in Glass Beads Strewn Across Moon appeared first on Futurism.

 
 
 
Microsoft's 'Security Copilot' Sics ChatGPT on Security Breaches
 
 
 
Feedly AI found 1 Partnerships mention in this article
  • Two weeks ago, the company launched Microsoft 365 Copilot, which builds on a partnership with OpenAI along with Microsoft's own work on large language models.
 
The new tool aims to deliver the network insights and coordination that "AI" security systems have long promised.
 
 
 
mRNA vaccines and hybrid immunity use different B cell germlines against Omicron BA.4 and BA.5
 
 
 
Is this article about Biopharma Industry?
 

Nature Communications, Published online: 28 March 2023; doi:10.1038/s41467-023-37422-y

Omicron strains of SARS-CoV-2 have displayed high transmissibility and immunological escape to antibody responses derived from natural infection and vaccination. Here the authors compare the antibody response to vaccination and natural infection, assessing neutralisation after vaccine doses and analyse the repertoire of such responses.
 
 
 
A holistic view on the role of egg yolk in Old Masters' oil paints
 
 
 
 

Nature Communications, Published online: 28 March 2023; doi:10.1038/s41467-023-36859-5

Old Masters used paints containing mixtures of oils and proteins, but we lack an understanding on how and why proteins were used. Here, the authors use egg yolk in combination with two pigments to evaluate how different repartition of proteinaceous binder can be used to control the flow behaviour as well as drying kinetics and chemistry of oil paints.
 
 
 
Would a corporation realistically release an AGI to the public?
 
 
 
 

Some people have the apprehension that the rich or the 1% will only keep the AI to themselves and block the access to the public. That would make sense, if they actually have an AI that's on the level of human intelligence or an AGI.

An AGI is basically a golden-egg laying goose for the corporation. They can just use the AGI to produce as much innovations as possible. If it really has human-level intelligence, then they can just fire every employee except for a few, and let the AGI do all the work. That is, if they actually have an AGI.

People believing the corporate PR that they have an AGI or "proto-AGI" are incoherent. Why would they release such a thing to the public? Why would they let their rivals have access to such a revolutionary tool? And why wouldn't they just start firing every one of their employee except for a few? I'll believe or speculate that they have an AGI once they start firing 99% of their employee.

So, either a corporation wouldn't release an AGI to the public, or they don't have one. Corporations are releasing AIs because it's something that is "moderately useful", but nothing revolutionary.

And in order to counter this, we'll need non-profit organizations making AIs, and not just believe whatever PR that the corporations come up with.

submitted by /u/Shiningc
[link] [comments]
 
 
 
Hanna Rosin named host of The Atlantic's weekly podcast, Radio Atlantic
 
 
 
 

The Atlantic has named a new host for its flagship podcast, Radio Atlantic: Hanna Rosin, a former Atlantic writer who was a co-host of NPR's Invisibilia and most recently the editorial director for audio at New York magazine. Hanna will bring her formidable talent and deep curiosity to Radio Atlantic, which will relaunch in the spring.

Radio Atlantic will resume a weekly cadence in late May. The show will have the same ambition as the magazine, which is to surface the most exciting and relevant ideas of the moment, whether through timely conversations or audio-rich reported stories. Like the magazine, it will feature a range of perspectives and journalism that makes you see the world differently.

"A good episode is one that gives you new insight, or a new way of thinking about a critical issue at exactly the moment when you, the listener, are looking for that guidance," says Hanna.

As a writer at The Atlantic in the early 2010s, Hanna wrote a series of memorable, high-impact cover and feature stories probing how we exist in the world: about the end of menoverprotective parents, and fraying teen mental health. She has since the summer of 2020 been the editorial director for New York magazine's audio unit, where she launched the shows Cover StoryInto It, and On With Kara Swisher, and oversaw the growth of Pivot. While at Slate, Hanna founded the section DoubleX and hosted the Waves podcast.

"Hanna is one of the most gifted journalists I've ever met," says Jeffrey Goldberg, The Atlantic's editor in chief. "She was an immensely successful feature writer for us, and so it was distressing when she left The Atlantic. But, of course, she succeeded wildly in podcasting, and it's a great joy to welcome her back home to The Atlantic, where she will contribute greatly not only to our ambitious audio strategy, but to all of our journalism."

The Atlantic is expanding its audio offerings in 2023 under the leadership of executive producer Claudine Ebeid, alongside Goldberg, executive editor Adrienne LaFrance, and managing editor Andrea Valdez. Earlier this month, The Atlantic launched the narrative podcast Holy Week about the uprisings that followed the assassination of Martin Luther King Jr. in 1968 and how those seven days––one of the most fiery, disruptive, and contentious weeks in American history––diverted the course of a social revolution. All eight episodes of Holy Week are available now.

Other recent editorial hires include Stephanie McCrummen as a staff writer, who started at The Atlantic after nearly two decades at The Washington Post, and Laura Secor as a senior editor to direct coverage of global issues and foreign policy. Laura was a features editor for The Wall Street Journal's Weekend Review, and previously a deputy editor at Foreign Affairs.

 
 
 
What American Liberals Can Learn From Israel's Protests
 
 
 
Is this article about Political Science?
 

Every visit I've ever made to Israel has included a screaming match with my relatives there. I know: They're Israelis. It's to be expected. It's how they show love. But the fights always resulted from the gentlest of prodding on my part—about the occupation, about the expanding role of religious authorities, about why Israeli taxi drivers can seem so obnoxious. They would respond with disproportionate defensiveness, even when I knew that my family of Tel Aviv centrists basically agreed with me. The questioning itself, especially from someone who didn't live there, was the problem. I would be reminded that only two paths were open to me—pro-Israel or anti-Israel—and that simply by opening my mouth I had made a choice, the wrong one. There are a hundred reasons not to criticize the embattled Jewish state, I was told, and that was doubly true for me, an outsider, an American.

This has made my extended family's WhatsApp group a confusing place for me recently. Until a couple of weeks ago, I had never seen my relatives at any protest (except maybe that one about the high price of cottage cheese). But every day, for weeks now, one of my uncles, Zvika or Doron, and my many young cousins have been posting photos and videos from the swelling demonstrations against the government of Prime Minister Benjamin Netanyahu over a bill that, if passed, would drastically curtail the power of the country's Supreme Court—calling into question, critics say, whether Israel could even be called a democracy anymore.

[David Grossman: Israeli democracy faces a mortal threat]

After Netanyahu fired on Sunday the one minister in his government who dared to question the speed with which the bill was proceeding through Israel's Parliament, those protests turned into a full-blown domestic crisis. By Monday, a huge bonfire could be seen burning wildly in the middle of Tel Aviv; strikes had shut down the airports, schools, and garbage collection. And there were my relatives, in the streets in the middle of the night, fire blazing behind them, chants filling the air, at the center of it all.

The success of this protest movement, which yesterday finally forced Netanyahu to postpone a vote on the bill, has to do, it seems to me, with the flags. They were everywhere, flung around shoulders, fluttering on long sticks, painted on young cheeks, stretched over the heads of crowds. There seemed to be no square foot without the blue Star of David. The protesters wrapped themselves in the flags: If there were indeed only two possible choices, this demonstration was unabashedly pro-Israel.

Those who came to resist Netanyahu and the moves of his extreme-right coalition partners avoided the framing of their actions as the expected leftist response—as a form of reaction, that is. They were the ones, they said, who were being true to the values of Israel. They were the ones who represented the Jewish and democratic state that Israel was founded to be. They were the authentic Israelis—even, one might say, conservative in the truest sense of hewing to tradition—while those looking to enact what they called "judicial reforms" were the dangerous radicals, the ones trying to bypass the rule of law and impose an alien authoritarianism akin to Hungary's.

[Yair Rosenberg: Netanyahu flinched]

This was a dramatic reversal of roles for a liberal sector of Israel society that has often been derided over the years as "elite" and out of touch, dismissed as caring more for the Palestinians than they do for their fellow Jews. The blatant, overwhelming patriotism on display at these protests made that characterization moot. If any opponents tried those insults, they were drowned out by boisterous, emotional singing of the Hatikvah, Israel's national anthem.

The patriotism allowed my relatives to take part. It helped release the cascade of support that the protesters have enjoyed in the past few days. "There comes a time in the history of a people or a person or an organization when you have to stand up and be counted," Daniel Chamovitz​​, the president of Ben-Gurion University, told The New York Times, explaining his decision to shut down the university in protest. Labor unions throughout the country followed suit. And, most crucially, large numbers of reservists in the Israeli army declared their refusal to serve when called up. To the attempt by right-wing government ministers such as Itamar Ben-Gvir to depict the protesters as "anarchists," the movement responded: We are just Israelis.

The bill has not gone away, and Netanyahu and his allies are determined to see it passed without compromise. But for a cohort of politicians loath to show weakness, the decision to delay was a sign that the protests are effective.

[Sasha Banks: The problem with patriotism]

The American left has not turned to Israel as a role model for anything for a long time. And normally, wrapping oneself in the national flag would be about the last thing any self-respecting U.S. liberal would be inspired to do—least of all by Israeli example. But nothing lately feels normal, and liberal values and democratic standards are in no great shape here, either. It might be time for American defenders of liberal democracy to consider waving our own flag with the same abandon as my Israeli relatives.

The left's allergy to exhibitions of patriotism has always granted the right an extraordinary rhetorical weapon: the chance to claim that the other side is not really American, does not really care about our country. It would be foolish to suggest that waving more flags would deny the right that weapon, but what's happened in Israel shows the tactical benefits of flipping this script, of loudly claiming authenticity and all that's positive about belonging to a nation.

[Ben Rhodes: This is no time for passive patriotism]

What if the left made its fights, whether over reproductive rights or gun control or any number of issues, in a more full-throated patriotic tone, as an expression of the country's deepest commitments to life, liberty, and the pursuit of happiness? Speaking in this register might be uncomfortable at first—less comfortable, certainly, than the vocabulary of progress, of a flawed society evolving to become better. But it would establish the left's causes as affirmations of a national identity, as true to tradition, making them much harder to brush away as un-American. If this came along with the outward symbols—the chants of "U.S.A.," the flags around shoulders—the right would find it harder to resort to its usual reflexes. You can't be called an out-of-touch elitist when you're loudly singing the national anthem.

Israel and the U.S. are two different societies, with two very different histories. But their politics have each become entangled in almost matching culture wars that are, essentially, about questions of authenticity and belonging. If Israel's streets today are any indication, the people usually on the defensive in these arguments have a lot to gain by simply exclaiming that they have as great a stake in the nation, that they are just as much the nation.

 
 
 
Scientists gain insights into Old Master artists' use of egg in oil paintings
 
 
 
 

Researchers believe egg was used by likes of Botticelli and Da Vinci for fine-tuning of oil paint properties

It pays to go to work on an egg when painting with oils, researchers have found, as the addition of yolk can prevent wrinkling, yellowing and problems with humidity.

The use of egg as a binding medium for pigments, a form of paint known as egg tempera, has a long history, turning up in works including the mural paintings of the Palace of Nestor in Pylos, dating to 1200BC.

Continue reading…
 
 
 
Technology and industry convergence: A historic opportunity
 
 
 
Feedly AI found 2 Partnerships mentions in this article
 

 

When seemingly disparate fields, industries, and ways of thinking merge, a convergence happens, which, has the power to build more intuitive and advanced futures for both organizations and the everyday consumer, says Accenture communications, media and technology industry group chair, Kathleen O'Reilly and Daniela Rus, Director of the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), and the Andrew and Erna Viterbi Professor in the Department of Electrical Engineering and Computer Science (EECS) at the Massachusetts Institute of Technology.

"Today, the kind of superpowers that seem to belong in storybooks can be achieved by mathematical models, computation, new materials, AI, robotics–this convergence of fields," says Dr. Rus.

This episode is part of our "Building the future" podcast series. It's a multi-episode series focusing on how organizations, researchers, and innovators are meeting our evolving global challenges. We understand the importance of inclusive conversations and have chosen to highlight the work of women on the cutting edge of technological innovation, and business excellence.

A combination of technology and human ingenuity will push boundaries as companies look to enter a new wave of innovation through data and AI to enable growth. Although O'Reilly estimates that we're in the early stages of this transformation, she predicts that this convergence will be the biggest change since the industrial revolution.

"We are seeing with the exponential pace of technological innovation, which we believe is going to continue, that this is really creating an opportunity for one of the most exciting periods of positive change and progress for all of history," says O'Reilly.

Much of this acceleration occurred over the course of these last pandemic years as many businesses and consumers alike take advantage of remote working operations including digital payments, telehealth appointments, and AR/VR experiences. But to anticipate and learn from the future, organizations and leaders always need to look to data and the insights derived from it.

"Intentional futurists," says O'Reilly, "use AI-based analysis to find patterns, anticipate trends, detect new sources of growth opportunities, understand their consumers, their customers, other enterprises, the markets and their employees better."

Practically, to bring this convergence from both leadership and academia, organizations need to be mindful of regulations and ethics to drive forward positive innovation and transformation.

"Whether you are a technologist, a national security leader, a policymaker or a human being," says Dr. Rus. "We all have a moral obligation to use the AI tools to make our world safer, and better, and to make the lives of our citizens safer and better in a just and equitable way."

This episode of Business Lab is sponsored.

Related reading

Full transcript

Laurel Ruma: From MIT Technology Review, I'm Laurel Ruma, and this is Business Lab, the show that helps business leaders make sense of new technologies coming out of the lab and into the marketplace. This episode is part of our Building the Future series. We're focusing on how organizations, researchers, and innovators are meeting our evolving global challenges. We understand the importance of inclusive conversations and have chosen to highlight the work of women on the cutting edge of technological innovation and business excellence.

Our topic today is convergence. Innovation thrives when ideas from various fields, industries, and ways of thinking merge. Building the future is a big task. Industries and fields of study need to be reimagined to make way for new opportunities. Enabling this will allow us as a society to learn from, act on, and build toward purposeful sustainability, insightful data and artificial intelligence, and a meaningful metaverse.

Two words for you: future forward.

My guests are Kathleen O'Reilly and Dr. Daniela Rus. Kathleen is the communications, media and technology industry group chair at Accenture and is a member of Accenture's Global Management Committee. Daniela is a professor of electrical engineering and computer science, as well as the director of the Computer Science and Artificial Intelligence Lab, or CSAIL at the Massachusetts Institute of Technology.

Welcome, Kathleen and Daniela.

Daniela Rus: Thank you.

Kathleen O'Reilly: Thank you. Wonderful to be here.

Laurel: So Daniela, let's start with you. What have you been working on that excites you, and what challenges are you preparing for?

Daniela: Thank you for this excellent question. So do you remember when Mickey summons the broomstick in the Sorcerer's Apprentice? I've loved this piece ever since I can remember. The idea that you can animate and control everything around you. This is magic to Mickey, but today you don't need magic to make that sort of thing happen. Today, the kind of superpowers that seem to belong in storybooks can be achieved by mathematical models, computation, new materials, AI, robotics, this convergence of fields. And I'm, for one, fascinated by all the superpowers we can achieve with these new technologies. I like to imagine a future with AI and robots supporting people with cognitive and physical tasks with the same pervasiveness with which smartphones support us with computing work. So how to get there? What do I do in order to aim in that direction?

Well, my current interests are to make more capable robots with softer bodies, better brains, whether the brains are for robots or other kinds of systems that are enabled by new models for machine learning, and to create more intuitive human/machine interactions with machines adapting to people, rather than the other way around. And so let me say a bit more about bodies and brains to be a little bit more concrete.

So the past 60 years have defined the field of industrial robots and have empowered hard bodied robots to execute complex assembly tasks in constrained industrial settings. Well, I believe the next 60 years we'll be ushering in robots in human-centric environments, and our time with robots helping people with physical tasks.

Now, while the industrial robots of the past 60 years have mostly been inspired by the human form, they are humanoids, they're robot arms, or they're boxes on wheels. The next stage will be soft robots inspired by the animal kingdom, with its form diversity, and also by our built environments. Imagine your chair turning into a robot. And the application potential is huge.

The other thing I'd like to observe is that while the industrial robots of the past 60 years are made of hard plastics and metal, I believe the next 60 years will bring us machines made of all types of materials available to us naturally, or through engineered processes. Wood, plastic, paper, ice, even food. So in my lab, we are developing computational approaches for designing soft robots that are made out of a wide range of materials, and also their brains that enable new applications. And so among these applications are robots that swim like fish and move like turtles, robots that brush your hair, robots that pack your groceries, and can reason about how not to put milk on top of bok choy. Robots that recycle, robotic pills that enable incision free surgeries. And in each of these advances, the body of the robot and the brain of the robot needs to be designed and need to be worked with in a slightly different way than we're currently used to.

And so I would just like to say a couple of words about these new ways, and in particular about the brains. Because this connects to the broader field of AI and machine learning. And so when it comes to brains, whether the brain controls a robot, or some other computational system, it is very important to know that today's greatest advances are due to decades old ideas that are enhanced by vast amounts of data and computation. And so we need new ideas, because without new technical ideas, more and more people will be staying within the same current techniques and deep neural networks, and the results will be increasingly incremental. And so how to do this? How can we get to the point where we imagine machine learning that is different from today's technologies, and what aspects of machine learning should we be thinking about?

Well, today's machine learning solutions also have some challenges. The first one is in the data. Today's AI methods require data availability. That means massive data sets that have to be manually labeled, and are not easily obtained in every field. The quality of the data has to be very high, and it needs to include critical corner cases for the application at hand. If the data is bad or biased then the performance of the model will be equally bad or biased. Furthermore, these systems are black boxes. There is no way for users to learn anything about how the system reasons by looking at the system's workings. And as a result, it is difficult to anticipate failure modes tied to rare inputs that could lead to potentially catastrophic consequences. And also we have robustness challenges. And so we need to understand that these systems do not do deep reasoning. They mostly perform pattern matching.

And so in my work, I am trying to address these current shortcomings of machine learning. In other words, brittleness, the huge size of the models, the large computation requirements, the lack of explainability, the bias. And what I'm most excited about is our new machine learning model we call liquid networks. This is a continuous time model with a novel equation for the artificial neuron that has biological inspiration, and also wiring between neurons that is inspired by the wiring in the brains of small species. And it turns out that this model, liquid networks, yields to compact explainable and provably causal solutions that even have close form approximations. So we do not need the heavy computational machinery of ODE solvers to train or do inference in these systems.

And so let me just give you a quick example. If you want a machine learning model to learn how to steer a car, well, if you use a deep neural network, then you are going to use about 100,000 neurons and a half a million parameters. A liquid network, for the same task, only requires 19 neurons, and this network has extraordinarily sharp attention. In fact, the liquid network will make decisions by looking at the road horizon, and by looking at the sides of the road at the road horizon, whereas a deep neural network will be looking at all the bushes on the side of the road. So there are so many advantages with these new types of machine learning, and I'm very excited about the potential.

Laurel: No, that's fascinating. But how do we specifically think about the evolution of technologies like machine learning in real world situations? You mentioned a robot pill, and I imagine soft robots can even reach places that others can't. So there seems to be a lot of possible applications there.

Daniela: Well, the possibilities are endless, and I'm especially excited about empowering people with what seems like superpowers that belong to storybooks. But I'm also interested in how these technologies are broadly impacting industries. And I believe that in the future, these new technologies have the potential to reduce and even eliminate car accidents. They have the potential to better monitor, diagnose, and treat disease. They will keep your information safe and private. They will transport people and things faster and cheaper. They will make it easier to communicate globally. They will deliver education to everyone. In other words, these technologies will allow human workers to focus on bigger picture tasks like critical thinking and strategy.

And all the fields that have data can benefit. And so for example, in medicine, we have a lot of data, and machines today can look at more radiology scans in a day than a radiologist will see in an entire lifetime. So let me give you an example from an experiment where machine learning and doctors were given images of lymph node cells, and were asked to diagnose cancer or not cancer. And on its own, the machine learning system had an error rate of 7.5%, which is worse than the 3.5% rate of the human pathologist. But when both the machine learning system and the pathologist worked together, the error rate went down by 80% to only 0.5%, which is extraordinary. So it's about how can we steer these tools to help empower us in our decision-making.

So now I would observe that today these systems may be deployed in the world's most advanced cancer treatment centers. But imagine a future where every practitioner, even those working in small practices in rural settings, had access to these systems. Where a doctor may not have the time to review every new study or clinical trial, but working in tandem with these systems, the doctor will offer patients the most cutting-edge diagnosis and treatment options. And these possibilities are so broad. They go beyond medicine, they impact every industry that has data, and that can really use machine learning and AI as an enabler. So this includes using AI and data driven decision making to improve organization efficiency, it includes using computation to create optimized, dedicated AI hardware, and then use it for new products.

So what is exciting is this convergence in interests between universities, where many of the new ideas originate, and companies which take the ideas and turn them into products. And I just want to say that university/industry collaborations can be a really solid foundation for this kind of future progress, because these university industry collaborations drive innovation. The relationships are symbiotic, with universities pushing the boundaries of knowledge, leading the science, training the future workforce, and companies having the opportunity to see around the corner, to see the next big ideas early and consider their implications.

In fact, there is an NSF program, it's called the NSF Industry University Cooperative Research Centers program. And as part of this program, it was calculated that every dollar put into a partnership by a company is leveraged 40 times. And so imagine all the possibilities when we think about the convergence between industry and the academy. There are so many opportunities.

However, I just want to end by saying to be successful, it is important to have the required AI infrastructure to have an educated AI workforce, and to have AI adoption and acceleration capabilities.

Laurel: Thank you, Daniela. You've certainly covered quite a bit. But Kathleen, I'm hooked on that idea of innovation and convergence and that idea of business and academia coming together. So what trends are you seeing within Accenture and with clients? How does that pairing of strategy and technology including bleeding edge technology that Daniela just worked us through, how can that help companies innovate?

Kathleen: Yeah, thanks Laurel. And I couldn't agree more with Daniela's point, and your question in terms of the power of the coming together of institutions that push the boundaries of science and technology knowledge and business. And that certainly underpins, I'll take your second part of your question first, is how do we see strategy and technology coming together? I think at the end of the day, where we are right now is that underpinning really any successful strategy, what we're seeing for clients that want to lead, for companies that want to lead, need to lead, and are pushing the boundaries, technology underpins those strategies. And we are seeing with the exponential pace of technological innovation, which we believe is going to continue, that this is really creating an opportunity for one of the most exciting periods of positive change and progress for all of history.

And it's that combination of technology and human ingenuity, as we say, and as Danielle just alluded to in her medical example on cancer treatment, that is really where the greatest value and the greatest impact is going to come. We believe the companies which are going to be leaders in the next decade are going to need to harness five forces, and all of these forces are going to require technology and ingenuity to come together. They're going to require organizations to work across all elements of their organization, to work with new partners, to expand into new areas and ecosystems, to learn and collaborate with innovators across industry, as well as across industry and academia and beyond to really push the boundaries of science and impact.

The five forces that we see right now, the trends that we're seeing that are impacting our clients the most really start with what we believe underpins everything right now, and that is something we're calling total enterprise reinvention. And we really started to see this come to the fore as we moved through covid. And what we're seeing now is that as companies are looking to enter these new waves of change and opportunity, that they're needing to execute strategies to change and transform all parts of their business through technology, data, and AI, as Daniela just talked about, to enable new ways of growth, new ways of engaging customers, new business models, new opportunities, but they're doing it in a very different way. They're doing it in a way where they're looking at every part of their organization and the technology and digital core that underpins it at the same time, so we believe we're in the early stages of this profound change, but we believe it's going to be the biggest change since the industrial revolution.

And embracing total enterprise reinvention often requires something that we call compressed transformation, which are bold transformational programs that, as I said, span the entire organization with different groups working together in ways that they never did before in parallel, but in very accelerated timeframes. And underpinning all this is leading edge technology, data, and AI. At the same time, the second trend we're seeing with our clients, and we certainly are all reading about it and of hearing about it for the past few years, is the power of talent and the importance of the human side of this equation. And we think that one of the forces that's going to shape the next decade with talent at front and center is not just the ability to access talent, but really for organizations to learn to be creators of talent, not just consumers. To unlock the potential of the humans in their workforce. And that's going to require technology to unlock that potential. And again, as Daniela just gave in some of her examples, to compliment the talent that they have in the organization.

The third is sustainability. That trend is … I would say personally, I'm very pleased to see this trend underpinning everything that we're doing and everything that our clients are thinking about right now. We believe that every business needs to be a sustainable business. And every industry is looking at this in a way that is unique to their industries. But whether it's consumers, employees, business partners, regulators, or investors, we know that we're moving in a direction where companies are being required to act. To make a change, not just around climate and energy, but areas like food insecurity and equality. All of those issues are coming to the fore, and underpinning this, again, is the ability to leverage new bleeding technologies to accelerate the pace of change and find solutions to the issues that we're facing as a planet and across society.

The fourth force that we're seeing is the metaverse. Now, there's been a lot of confusion, and a lot of talk about the metaverse, but our view is that the metaverse is a continuum, and we're seeing this come to the fore in the marketplace right now. As we look at the metaverse and how that's going to impact, just if you think all the way back to when the internet was in its early stages, we believe that the impact is going to be that great. And while it's early stages and not everybody can see exactly how the impact is going to be there, we believe that this is going to impact not just consumers, and of course interesting areas like virtual reality and using AI to bring new experiences to life, but also to look at extended reality, to look at digital twins, smart objects. So how do cars and factories run? What's happening with edge computing? Looking at blockchain and new ways of payment. All of those things are going to change the way businesses operate and really the way society operates, and we believe that this is going to underpin change as we move forward over the next five to 10 years.

And then lastly, the fifth force is what we're calling ongoing tech revolution. And the ongoing tech revolution is a pretty broad expansive category, often pushed by our friends in the academia world around science, but we believe in the coming decade, the pace of technological innovation is not just going to continue but accelerate, which we believe is going to create positive change. New technology, whether it's in quantum computing or it's in areas, as I said, like blockchain or material science or biology, or even space, we believe this is going to open brand new areas of opportunity. And all of these things are allowing companies, our clients to find new ways to not just serve their customers, but to monetize their investments, to impact society, to impact their employees, and to drive positive change for their business as well as for the world around them.

Laurel: Yeah. Kathleen, I feel like some of that acceleration happened in these last few pandemic years so that businesses and consumers are operating differently from remote healthcare solutions to digital payments, greater expectations of those immersive virtual experiences. But how can organizations and technologists alike then continue to innovate to anticipate the future, or as Accenture likes to say, learn from the future? You have some good examples there, but the five different areas all kind of also lead to this acceptance of change.

Kathleen: Yeah, they do. And they also lead to embedding data in everything, in new ways into every change that organizations are putting forward. When we think of learning through the future, we think about organizations and leaders who are constantly seeking new data and insights, not just from inside their organization, but from outside their organizations' four walls. So we like to use the phrase intentional futurists. These are people and leaders and organizations who use AI-based analysis to find patterns, anticipate trends, detect new sources of growth opportunities, understand their consumers, their customers, other enterprises, the markets and their employees better.

For example, we know AI is transforming agriculture at a time when climate change, as I just referenced with sustainability, makes feeding the world more challenging than ever. Not to mention some of the broader issues that we're all seeing emerge around the world from a geopolitical standpoint. Advanced agricultural technologies employee sensors, cameras, connectivity to collect and process historical and real time data on planting conditions, weather patterns, and crop health. And AI enables the farmers to manage at the individual plant level and optimize their production around consistent high-quality crops. It's technology and the use of technology combined with the human side that is going to drive that kind of change.

And we know that covid prompted an acceleration into these areas of businesses wanting to learn from the future, see around the corners, if you will, understand those patterns as well as invest more quickly into new technologies, particularly cloud platforms. And with those cloud platforms comes the privilege, and I would say the responsibility, of having access and use of significant amounts of data. And with responsibility, Daniela, I'll reference what you just talked about for example, ensuring that responsible AI and how bias is handled is an example. These are new areas that we need to be thinking about, but we also know that in the next frontier of better data utilization, we have to think differently about how we use AI.

We believe that by 2025, we're going to create an estimated 180 zetabytes of data. But right now, only 11% of the data created and captured is useful for analysis, and only 44% of that data is actually used in practice. So we are completely under-utilizing what we have access to, and we need to think about that. Accenture publishes a tech vision every year, and we call this computing the impossible. So how do you use high performance computers or parallel processing supercomputers to more quickly synthesize data and forecast outcomes, and figure out new areas of opportunity, new possibilities in solving big issues? we know that innovation's all about creating those new ideas and that data's going to underpin that, but again, when combined with the power of human ingenuity to design the strategies and how to use these things responsibly.

Daniela: So if I might just jump in, I just want to underscore what you have just said, Kathleen. The under-utilization of data is extraordinary, and we really need to be thoughtful about how to move forward. We need to find which data is important data and which data is not so important, and then we need to see how to harness the important data.

Kathleen: Absolutely.

Laurel: And I love that phrase, intentional futurist. Daniela, what you were talking to us before really sounds like that, doesn't it? So if successful innovation is a convergence of those types of ideas, industries, and those lines of research, how are you seeing this actually play out in practice?

Daniela: Well, so I loved what Kathleen called compressed transformation, with different groups of people coming together. And I think this is exactly how we need to think about bringing the greatest ideas from the academy together with the greatest business minds to make practical impact on the world. But we need to be thoughtful and careful about creating private/public government partnerships that leverage the contributions of each entity. Because new products require the exciting ideas from the academy, they require the business minds of the people who understand what is marketable and useful and what is not, but then it also requires the policy side, it requires the regulation that talks about how all of this should be done in a way that is positive for the world.

And so this kind of convergence of people with different backgrounds and different lenses, about the ideas and the technology is important. And I'd like to give you an example. In 2019, MIT started a research partnership we call the AI accelerator, where the accelerator's objective is to speed up the development of the science of AI, and also of the path from research to innovation and domain relevant products. Now, the current partnership is between MIT campus, MIT Lincoln Lab, and the U.S. Air Force, and together these three entities are defining a converging fruitful collaboration, with contributions to science and knowledge in general, but also with the aim of bringing the rapidly developed new tools and innovation to national security. And we have MIT researchers who are leading the development of the science, and they're working shoulder to shoulder with Lincoln Lab and Air Force researchers.

So we have these integrated teams that bring all the stakeholders to the same level of knowledge and understanding. And then the idea is that Lincoln Lab and Air Force can partner on developing products beyond the research grade ideas that are being developed as part of this program. And applications in diverse areas such as disaster relief, weather modeling, which is so important for understanding climate, medical readiness, and really many other broad societal topics that are of great interest to the world. And so these interdisciplinary teams with experts from AI, from MIT, domain experts from the Air Force, and experts from MIT Lincoln Lab who understand both AI and the domain accelerate both the science advances, but also the adoption of AI in the DOD [U.S. Department of Defense]. So this is an example of how converging teams can really speed up the innovation, and also the adoption of that innovation.

So let me also say that broad adoption of AI also requires collaborations with policy makers who ensure that the deployments are positive and support the greater good. So we need conversations between technologists, business leaders, and policy-makers to get to positive and responsible adoption and deployments. But we don't need our policy-makers to understand the intricate mathematical details of how AI works. However, we do need to educate everybody, our leaders and our citizens broadly about technology and about the impacts of our choices so that we can make the right ones. And I believe that it's important to think about five vital questions in order to build a common understanding.

The first question is what can we do? In other words, what's really possible with technology, and where can we improve? The second, what can't we do? In other words, what is not yet possible? Then we have to think about: what should we do? What shouldn't we do, because there are things about technology that we should rule out. For example, we shouldn't be building better tools to enable this information. And also, finally, what must we do? Because I believe we have an obligation to consider how AI and machine learning can help, because ultimately this is what it's all about. And whether you are a technologist, a national security leader, a policymaker or a human being, we all have a moral obligation to use the AI tools to make our world safer, and better, and to make the lives of our citizens safer and better in a just and equitable way.

Laurel: Yeah, I like that idea of really bringing it home, because it is for each person as well to have a safer and better life. So Kathleen, that same question to you. How is this convergence of ideas coming through in practice from leadership and research and industry innovation?

Kathleen: Yeah, we're definitely seeing it from a business perspective also. First of all, we're certainly seeing companies and leaders looking across industries to make sure that they're learning from others, and how they're using assets and tools and what new methodologies are making a change in their business. They're applying what others are learning quickly. I actually think that what we saw happen in the pharmaceutical or life sciences industry during covid was the beginning of, my own observation, a new period of collaboration both within industry, certainly within organizations, across organizations as I've referenced earlier, but within industries and across industries. And we're seeing leadership driving for, "Yes, I need to understand my market, my business, my customers, but I also need to understand how everybody else is using innovation and technology out there, and making sure that they're learning versus reinventing a wheel, because there's an imperative to move quickly."

We're also seeing that, of course, clients and their partners are diversifying, entering new and adjacent industries, anticipating trends, understanding what's happening where there may be some new value pools. Those are probably more some of the more obvious areas. And certainly an example of this could be in e-commerce, something we've been talking about for years, I guess decades at this point. Advancements in consumer goods and new insights in that area, or in let's say banking or security, are actually shaping, in my world, how some of the social platforms are thinking that they will advertise and monetize those investments and set up new marketplaces while also protecting their data.  We're seeing industries learning from each other.

If I take it a step further, I'll go to the high-tech industry, in looking at how do you enable double digit growth or long-term growth? Trailblazers in this industry are really looking at other industries and new parts of the value chain. We recently did a survey of high-tech industry executives, and 87% of them agreed that convergence is a growth enabler, that multiple industries are ripe for tech led disruption, and that the high-tech company skills and capabilities are going to be able to change those industries and create new opportunities. Three examples of this, automotive. We often hear about smart mobility, whether it's autonomous boats and cars and trucks or drones, military vehicles, all of those areas. How is that coming to the fore and what will that change? And again, I'll harken back to my earlier statements where these forces kind of tie together. It also ties to ensuring that sustainability is built into everything that we're doing, leveraging that new technology.

Another area is connected infrastructure. Certainly I spend a lot of time with my clients talking about edge and 5G enablement and the use cases for 5G is that comes into the fore. So think of things like smart buildings, smart grid. What are the energy and utilities companies doing to manage their businesses, and how can that be leveraged? Or another area that probably all of us are experiencing is digital health. AI powered smart hospitals, fitness wearables. Probably all of us have seen those, if not are wearing them ourselves, or even during covid if you think about contact tracing and some of the apps that came up there.

In all of these areas, we're seeing industries looking across industry both to learn, as well as to expand, and to innovate together.  It's creating new solutions, and it's a new approach to R&D and product development with a real customer-centric lens. It's finding ways to leverage your installed base to find new markets and capitalize with new products. It's enabling new strategic alliances that we're seeing pop up across the board, and sometimes those cannibalize parts of businesses, but almost always lead to new innovative areas that drive greater value. And then certainly we're seeing some inorganic change with mergers and acquisitions and new capabilities and organizations coming together in different ways.

And then lastly on leadership, I would say there has been, happily, a really big push on creating cultures of innovation. And not just creating a culture and a mindset for innovation but underpinning that with a culture of diversity and equality, which we know really puts the structure in place for innovation to take place wherever that may happen.

Laurel: I like the idea of having structure in place for innovation. Then you're actually building that as part of the culture of a company, of a group of people, a group of ideas. You did mention though, smart grids and smart buildings and this idea of sustainability. Why is it so critical to address big challenges like this, like sustainability, with an inclusive approach to innovation?

Kathleen: Yeah, yeah. No, that's a great question, Laurel. I would say sustainability is one, but I've mentioned a few times, at least our perspective, we look at impact in businesses, but also in society as a whole. Some of the biggest issues we're facing are going to require us coming together in different ways. Hopefully covid and that pandemic are more in the rear-view mirror than not. But disruption is going to continue and the unexpected is going to happen, and we need to be prepared for that. And in order to be prepared for that, we need to be prepared to come together in an inclusive way, both within organizations, and again, across organizations. And certainly by intentionally engaging people, whether it's a broader set of employees, a broader set of stakeholders or companies or markets, or even customers…under-tapped, underserved populations, the voices that we haven't traditionally heard from. The data tells us that it drives a stronger, broader set of thinking and pushes us into new areas and expands ways of thinking that wouldn't normally happen if you don't have all the right voices in the room, if you will. Even if it's a virtual room, which we certainly know that new technologies and new areas like the metaverse are going to allow us to bring people together in ways that never could have happened before, hopefully to solve problems in a much more inclusive and rapid way.

But bringing those voices together is maybe a statement of the obvious, but we also know that there's some data behind this. Accenture's research tells us that in organizations with an innovation mindset, but that also has an equal culture, and this is just within organizations, that the innovation mindset is six times higher in organizations or companies that have more equal cultures than least equal ones. We know that employees in equal cultures where they are included and brought together in ways that allow their voice to be heard, see much less in terms of barriers to innovation. As a matter of fact, in organizations that are more equal in their approach and have more of an equality and diverse viewpoint mindset, 40% of the employees see that nothing stops them from innovating, versus in organizations that don't have that kind of a mindset, only 7% believe that they can innovate.

And first of all, there's just something underpinning about bringing all those pieces together, but there's also data that says that drives a very different set of outcomes. If you think about solving for sustainability, which is one of the big, big issues of our day, and in this case let's just talk about climate because I've mentioned that before. That's going to require all of those voices to be heard and all of the perspectives.

We also see that organizations are using inclusion to underpin their growth strategies. So many companies need to reach new customers, new markets, they need to achieve their growth ambitions, but they need to get beyond their current target audience, if you will, and to reach unreached populations or underserved populations. In order to reach them, you need to innovate with inclusion in mind. So in the tech world, my world, tech companies have a business imperative to close the digital divide. There are three and a half billion people in the world that are not using the internet because they don't have access, or lack the digital literacy needed to benefit from that revolution that we've all benefited from.

Companies like Google, with their Next Billion Users initiative, are innovating inclusively to reach those consumers, and of course that will allow them to continue to innovate. Same thing in banking. Two billion adults don't use formal financial services. Leaders like MasterCard, in order to grow, are designing inclusive ways to address the pain points of these people, whether it's small farmers, factory workers, low-income consumers, and that financial inclusion is going to not just benefit society, but also benefit the businesses that are doing that. And the same thing happens with employees, as I mentioned. If you include employees in a different kind of way, you're going to get a very different outcome, from a business perspective, in terms of their ability to see new solutions and help drive your business forward.

And so if you go back to sustainability, in order to solve the issues that we're seeing around sustainability and particularly climate, we know that we need to think broadly and bring all the skills to the table on this. And whether that is technological innovation and the knowledge that's around things like digital twins, or creating physical prototypes, or use of blockchain to enhance traceability, AI to understand customer experiences, all of these areas are critical for us to solve the crisis in front of us from a sustainability standpoint, particularly a climate standpoint. And we know that that's going to take all those voices being at the table.

Laurel: And Daniela, Kathleen just really outlined some great examples of the challenges that enterprises have with not just sustainability, but also artificial intelligence and building the next future of work. How can artificial intelligence and other technologies help with these big challenges?

Daniela: So yes, I so agree with everything Kathleen explained about how diversity drives innovation and drives better solutions.

Now, sustainability, we can talk about sustainability at multiple levels. And I would like to start by underscoring that from a planetary point of view, AI can play an enormous role in sustainability, and it can do so by generating better insights, by helping us to collect and analyze data from vast sensor networks that monitor the oceans, the greenhouse, climate, other planet conditions. AI can also help businesses better monitor how they are expending and using their resources with a sustainability goal in mind. AI innovations can help optimize all our activities, and our carbon footprint and our energy footprint to slow the impacts of warming. And this is whether through optimizing the electricity utilization, the electricity cost of technology, making transportation more efficient, and also in other areas like monitoring and stopping deforestation, preserving biodiversity, ensuring that there is enough foods to go around, and food does not get wasted. But to do all of these things, whether at the planetary scale, at an individual scale, or for a business, AI systems consume enormous amounts of energy. And it's important to talk about that.

Researchers at the University of Massachusetts at Amherst estimated that training a medium sized language model produces 626,000 pounds of carbon dioxide. This is equal to the lifetime emissions of five cars. That's an enormous amount of energy, and a lot of these models are being trained right now. And so that's just for one average model. I also know that it costs $4.6 million in energy to train the GPT3 language model, which is the foundation of the recently released ChatGPT you may have played with. So the more pervasive AI becomes, the more of these models will be needed. And these examples really highlight a place where policy action to combat emissions and to invest in renewable forms of energy can complement technological improvements. But technological improvements are critical.

The AI systems are so costly because each one contains hundreds of thousands of artificial neurons, and millions of interconnections. And so if we can develop simpler models, this can drastically reduce the carbon footprint of AI and make machine learning technology more sustainable. Now, some companies are placing their data centers next to renewable energy sources as a potential solution, but there is also the opportunity to tackle some of the questions around the size of the model. We are already making progress on creating simpler models. For example, our own work with closed form liquid networks aims to provide a more sustainable solution for machine learning.

Laurel: Thank you. And Kathleen, just thinking about this as a holistic kind of view, there's so much in this one conversation that we've had. So much possibility and opportunity. How do you see the ideas of convergence really evolving in the next three to five years? Because there is that immediacy, there's an urgency, and there's sort of an excitement to, actually, let's get on with it.

Kathleen: Yeah, well I think the first thing is I think it's going to continue to accelerate as technological change pushes all of us, and the needs of businesses and the needs of our world push us. That urgency to move on and to push our thinking are going to force us into even new ways of bringing new ideas, converged ideas, collaboration to the table. And so I think over the next three to five years, besides just the acceleration, one of the things that we think is going to continue to accelerate is various organizations coming together in new ways. If we think about how one can leverage all those five forces, we believe that the continuation of that change in technology as that advances and critical talent and natural resources become more scarce, organizations may need to come together in different ways, and that may mean even formally.

We believe that the pace of M&A, as well as even divestitures, to streamline core competencies, to bring new capabilities together in new ways, different business models, different organizational models will continue to accelerate. We're certainly seeing that. 36% of M&A deals, according to our research, have the main motivation right now to acquire new innovative technologies and capabilities. And this is up as much as four to five times in certain industries like the health industry, the life sciences industry, the chemicals industry, and beyond. And so bringing new capabilities together as well as streamlining for capabilities and understanding what you need and what you can borrow from others, what you can partner with others in your ecosystem is going to accelerate.

The second thing that I think we believe about some of these more structural changes is that if you look at the technology sector, where I spend the majority of my time, inquisitive companies in the technology sector over the past few years, where we've seen a lot of activity, have generated 95% more return for shareholders compared to the sector average. So again, I think that's going to continue to push the thinking in that space.

We also think that organizations will continue to, as I mentioned, streamlining their core competencies, have an openness more of an openness to shared capabilities. Whether that's front and back offices, services or consortiums among companies who may at one time have been competitors but recognize that if they come together in new and appropriate ways, they can bring some new capabilities and new solutions to market. So we believe we're going to see more of that.

And I think if you look across the next three to five to 10 years, what we know is that the future that's in front of us for all of these companies is going to be completely different than probably what they were originally designed for. So over the next decade, we believe most companies, as I mentioned, are going to completely need to transform their business. And that's going to mean transforming the environment in which we do business. It also means that they're going to need to accelerate their investment in technology, so we believe that that's going to continue to move forward to really … Whether that's on delayed cloud migrations, or whether it's their use of AI and analytics, and those things that have been sidelined in the past, most clients we're talking to are saying, "How do I go faster? I can see the power of this. I can see the power of technology, and if I don't invest, I'm going to be left behind." And we believe that that day for investing, accelerating in the digital, accelerating technology, accelerating in data and AI is only going to move more quickly as we move forward.

Laurel: And Daniela, same question for you. How are you seeing these next three to five years, and how convergence will evolve and really accelerate?

Daniela: So I don't know exactly what will happen, but I would like to highlight three things that I would like to see happen. And the first one is about seeing more programs like the MIT AI Accelerator program. Because the convergence of expertise across disciplines and across public private government partnerships will truly enable great growth. University private partnerships are symbiotic, and they will enable innovation and progress.

I believe we will also see broader adoption of AI with tools like ChatGPT that are developed within a research context, but that will be adopted within a business context. And we will see new ideas and new applications of AI to enable discovery, and address some of the grand challenges that companies are facing and also that humanity is facing. And many of these challenges can only be addressed in a multidisciplinary way.

Second, I believe we will get serious about sustainability, and in particular about sustainable AI and sustainable technologies. This is important from a technological development point of view. This is also critical for the future of our planet and everything that lives on it. And third, I think we will get more serious about AI and privacy, because privacy is an example where the underlying technology needs to evolve. And it's super important since machine learning is so rooted in data. For example, AI and computation holds so much potential to help in areas like healthcare. And I just want to highlight that MIT researchers were able to leverage AI to synthesize a new antibiotic, the first one created in 40 years. And this has created an opportunity for us to imagine if this work could be extended to synthesize customized medicines, allocated to individuals based on their environment and circumstances, and generated on the fly. So I don't mean personalized healthcare, I mean individualized healthcare. An individualized cocktail of pills that is just right for the patient.

But of course to get there, we need data. And any time we use data, we need to consider risks to privacy, whether it's in healthcare or in insurance, or in any other industry. So we can address the privacy challenge with regulation, but technological breakthroughs can also make this easier. And we are already seeing great advances in homomorphic encryption that allow us to use data without decrypting it. And so organizations that need information, for instance your insurance company can post queries against a vast pool of data without ever decrypting the data itself. And so if we can get this right, we can create and learn from the largest pools of knowledge ever created and never risk the types of exposures that we see today. So I'm a technologist optimist, and I believe that these positive advancements and positive outcomes can happen, and will happen, especially if we have conversations like this one today.

Laurel: Excellent. Daniela and Kathleen, thank you so much for joining me today on the Business Lab.

Kathleen: Thank you for having us.

Daniela: Thank you very much.

Laurel: That was Kathleen O'Reilly of Accenture and Daniela Rus of MIT, who I spoke with from Cambridge, Massachusetts, the home of MIT and MIT Technology Review, overlooking the Charles River.

That's it for this episode of Business Lab. I'm your host, Laurel Ruma. I'm the global director of Insights, the custom publishing division of MIT Technology Review. We were founded in 1899 at the Massachusetts Institute of Technology, and you can also find us in print, on the web and at events each year around the world. For more information about us and the show, please check out our website at technologyreview.com.

This show is available wherever you get your podcasts. If you enjoyed this episode, we hope you'll take a moment to rate and review us. Business Lab is a production of MIT Technology Review. This episode was produced by Giro Studios. Thanks for listening.

This content was produced by Insights, the custom content arm of MIT Technology Review. It was not written by MIT Technology Review's editorial staff.

 
 
 
 
Is this article about Cell?
 
With CRISPR-Cas9 technology, humans can now rapidly change the evolutionary course of animals or plants by inserting genes that can easily spread through entire populations. Evolutionary geneticist Asher Cutter proposes that we call this evolutionary meddling "genetic welding." In an opinion paper published March 28 in the journal Trends in Genetics, he argues that we must scientifically and ethically scrutinize the potential consequences of genetic welding before we put it into practice.
 
 
 
Temperature-dependent adaptations of whale shark vision
 
 
 
 
Researchers in Japan led by the RIKEN Center for Biosystems Dynamics Research, Kobe and Osaka Metropolitan University, Osaka, have discovered that whale shark vision has uniquely temperature-dependent adaptations unseen in any other lifeform. They have detailed the findings in a study titled "Whale shark rhodopsin adapted to deep-sea lifestyle by a substitution associated with human disease," published in the Proceedings of the National Academy of Sciences.
 
 
 
The powerhouse of the future: Artificial cells
 
 
 
Is this article about Energy Industry?
 
Energy production in nature is the responsibility of chloroplasts and mitochondria and is crucial for fabricating sustainable, synthetic cells in the lab. Mitochondria are not only "the powerhouses of the cell," as the middle school biology adage goes, but also one of the most complex intracellular components to replicate artificially.
 
 
 
Using bacteria to convert CO2 in the air into a polyester
 
 
 
Is this article about Airline Industry?
 
A team of chemical and biomolecular engineers at Korea Advanced Institute of Science and Technology has developed a scalable way to use bacteria to convert CO2 in the air into a polyester. In their paper, published in Proceedings of the National Academy of Sciences, the group describes their technique and outline its performance when tested over a several-hour period.
 
 
 
 
Is this article about Cell?
 
With CRISPR-Cas9 technology, humans can now rapidly change the evolutionary course of animals or plants by inserting genes that can easily spread through entire populations. Evolutionary geneticist Asher Cutter proposes that we call this evolutionary meddling "genetic welding." In an opinion paper published March 28 in the journal Trends in Genetics, he argues that we must scientifically and ethically scrutinize the potential consequences of genetic welding before we put it into practice.
 
 
 
 
 
Researchers in Japan led by the RIKEN Center for Biosystems Dynamics Research, Kobe and Osaka Metropolitan University, Osaka, have discovered that whale shark vision has uniquely temperature-dependent adaptations unseen in any other lifeform. They have detailed the findings in a study titled "Whale shark rhodopsin adapted to deep-sea lifestyle by a substitution associated with human disease," published in the Proceedings of the National Academy of Sciences.
 
 
 
 
Is this article about Energy Industry?
 
Energy production in nature is the responsibility of chloroplasts and mitochondria and is crucial for fabricating sustainable, synthetic cells in the lab. Mitochondria are not only "the powerhouses of the cell," as the middle school biology adage goes, but also one of the most complex intracellular components to replicate artificially.
 
 
 
 
 
The precise measurement of biomolecules can play a critical role in improving our understanding of fundamental life processes. In a large-scale comparative study involving 19 laboratories around the globe, a team working with LMU scientists Professor Thorben Cordes and Professor Don C. Lamb, alongside Professor Claus Seidel of HHU in Düsseldorf and Dr. Anders Barth of Delft University of Technology, has now tested a method of measuring the precise dimensions and comparability of biomolecules.
 
 
 
 
 
Research into the unique cognitive abilities of dogs often leads to surprises, including dogs' ability to form mental representations of things they smell, or that they know when their owners do something by accident. However, dog cognition research suffers from the same biases as general psychology: in both fields, studies are usually done in WEIRD (Western, educated, industrialized, rich, and democratic) societies.
 
 
 
 
Is this article about Animals?
 
A small team of environmental scientists from several institutions in Italy and Switzerland has found evidence suggesting that at least some of the red plumage sported by barn owls on small, isolated islands may be due to the ingestion of sulfur. In their study, reported in the Journal of Biogeography, the group studied the preserved skin of thousands of barn owl specimens from multiple geographic locations archived in museum collections.
 
 
 
Smell-Loss Tests Could Reveal Health Problems
 
 
 
Feedly AI found 1 Participation in an Event mention in this article
  • The Monell Center, STANA and many other organizations are currently planning a conference to bring together scientists, clinicians, public health officials and people with smell and taste disorders to further workshop how to make universal chemosensory testing a reality.
 

Unlike other senses, smell is not something doctors routinely test for—but some scientists think that should change

 
 
 
 
Is this article about Airline Industry?
 
A team of chemical and biomolecular engineers at Korea Advanced Institute of Science and Technology has developed a scalable way to use bacteria to convert CO2 in the air into a polyester. In their paper, published in Proceedings of the National Academy of Sciences, the group describes their technique and outline its performance when tested over a several-hour period.
 
 
 
 
 
The precise measurement of biomolecules can play a critical role in improving our understanding of fundamental life processes. In a large-scale comparative study involving 19 laboratories around the globe, a team working with LMU scientists Professor Thorben Cordes and Professor Don C. Lamb, alongside Professor Claus Seidel of HHU in Düsseldorf and Dr. Anders Barth of Delft University of Technology, has now tested a method of measuring the precise dimensions and comparability of biomolecules.
 
 
 
 
 
Research into the unique cognitive abilities of dogs often leads to surprises, including dogs' ability to form mental representations of things they smell, or that they know when their owners do something by accident. However, dog cognition research suffers from the same biases as general psychology: in both fields, studies are usually done in WEIRD (Western, educated, industrialized, rich, and democratic) societies.
 
 
 
How to protect the integrity of survey research: 12 recommendations
 
 
 
Is this article about Market Research?
 
Science requires data, and survey research is one important means of gathering it. Surveys provide a scientific way of acquiring information that is used to inform policy decisions, guide political campaigns, clarify the needs of stakeholders, enhance customer service, help society understand itself, and improve the quality of life in the United States.
 
 
 
 
Is this article about Animals?
 
A small team of environmental scientists from several institutions in Italy and Switzerland has found evidence suggesting that at least some of the red plumage sported by barn owls on small, isolated islands may be due to the ingestion of sulfur. In their study, reported in the Journal of Biogeography, the group studied the preserved skin of thousands of barn owl specimens from multiple geographic locations archived in museum collections.
 
 
 
Nvidia Wishes People Would Stop Using Its GPUs to Mine Worthless Crypto
 
 
 
 
Nvidia has had enough. It's calling for its customers to stop mining worthless crypto and use its cards for AI instead.
 
 

Good for Society

Nvidia

, the video card giant whose sophisticated GPUs have found a weird new use to mine cryptocurrency, has had enough.

It's calling for its customers to stop mining crypto — and do something more worthwhile with their time.

The company's technology officer Michael Kagan recently told The Guardian that he wished buyers would turn their attention to artificial intelligence instead.

"All this crypto stuff, it needed parallel processing, and [Nvidia] is the best, so people just programmed it to use for this purpose," he told the newspaper. "They bought a lot of stuff, and then eventually it collapsed, because it doesn't bring anything useful for society. AI does."

"I never believed that [crypto] is something that will do something good for humanity," he added. "You know, people do crazy things, but they buy your stuff, you sell them stuff. But you don't redirect the company to support whatever it is."

Moving On

Kagan's comments aren't exactly surprising — the fact that the company still actively sells GPUs advertised as crypto mining cards, notwithstanding, of course. The crypto industry has been put through the wringer throughout 2022, with the value of mainstream cryptocurrencies like Bitcoin losing over half of their value.

Meanwhile, crypto miners have had to change tack, suddenly faced with an extremely expensive pile of largely worthless mining hardware. Major crypto lenders are selling off millions of dollars worth of mining rigs as they look for the next big thing.

And Nvidia sees a new opportunity on the horizon with AI, a technology that has caught on like wildfire with investors.

"With ChatGPT, everybody can now create his own machine, his own program: you just tell it what to do, and it will," Kagan told The Guardian. "And if it doesn't work the way you want it to, you tell it 'I want something different.'"

The appetite is certainly there, with AI already turning into a cash cow for the chipmaker.

Earlier this month, Microsoft announced it had bought tens of thousands of A100 GPUs, chips designed from the ground up with AI processing in mind. Amazon and Oracle have also bought similar offerings from Nvidia.

Of course, all that's assuming that crypto's moderate rally over the past month doesn't continue, breathing new life into the mining industry.

More on Nvidia: Horrifying Algorithm Locks Your Gaze Into Your Webcam

The post Nvidia Wishes People Would Stop Using Its GPUs to Mine Worthless Crypto appeared first on Futurism.

 
 
 
AI Seems to Do Better on Tasks When Asked to Reflect on Its Mistakes
 
 
 
 
A team of AI scientists is claiming that just like humans can solve problems through self-reflection, Large Language Model (LLM) AIs might be able to, too.
 
 

In a not-yet-peer-reviewed paper, a team of researchers from Northeastern University and the Massachusetts Institute of Technology suggests that large language models (LLM) might be able to learn from their own mistakes — just like humans.

Teaching them to do so, they say, might be able to push AI technologies into a new phase of autonomous problem-solving.

"Self-reflection allows humans to efficiently solve novel problems through a process of trial and error," the researchers write in the paper. "Building on recent research, we propose Reflexion, an approach that endows an agent with dynamic memory and self-reflection capabilities to enhance its existing reasoning trace and task-specific action choice abilities."

In other words, their methodology dubbed "Reflexion" is a framework for teaching AI models via prompts to apply a trial-and-error technique to their outputs.

So, just like us, if at first, they don't succeed, they can try, try again.

Testing their new framework was a relatively simple process. The machine, or "agent," was presented with problem-solving tasks and asked to complete them; when it messed up, it was prompted with the Reflexion technique to find those mistakes for itself — a process that they claim helps the program evolve, just like humans.

"To achieve full automation, we introduce a straightforward yet effective heuristic that enables the agent to pinpoint hallucination instances, avoid repetition in action sequences, and, in some environments, construct an internal memory map of the given environment," the researchers write in their paper.

Using a series of standardized "decision-making tasks," the researchers found that their methodology was able to greatly improve on a model's given success rates.

The scientists note that their research was conducted using GPT-3 and GPT-3.5-powered AIs — an important consideration, given that OpenAI just released the much more powerful GPT-4. Although, in an accompanying blog post that discusses the paper, the scientists say that when applied to GPT-4, a "slightly-improvised Reflexion-based GPT-4 agent" was correct 88 percent of the time, outperforming its 67 percent success rate pre-Reflexion.

Again, this paper isn't peer-reviewed, so definitely take the researchers' results with the usual grain of salt.

That said, AI programs mess up a lot, and as they continue to be embedded into workflows across industries and platforms, frameworks for addressing their pitfalls are certainly needed. While this research is more or less an exercise in prompt engineering — rather than addressing the problem of hallucinations from the inside out — it could help in the development of tools that can verify the infamously unreliable output of AI language models.

Besides, a little self-reflection never hurt anyone — human or machine.

More on machine hallucinations: Researchers Find Gpt-4 Is Significantly Less Accurate than Gpt-3

The post AI Seems to Do Better on Tasks When Asked to Reflect on Its Mistakes appeared first on Futurism.

 
 
 
ChatGPT Has Impostor Syndrome
 
 
 
 

Young people catch heat for being overly focused on personal identity, but they've got nothing on 

ChatGPT

. Toy with the bot long enough, and you'll notice that it has an awkward, self-regarding tic: "As an AI language model," it often says, before getting to the heart of the matter. This tendency is especially pronounced when you query ChatGPT about its own strengths and weaknesses. Ask the bot about its capabilities, and it will almost always reply with something like:

"As an AI language model, my primary function is …"

"As an AI language model, my ability to …"

"As an AI language model, I cannot …"

The workings of AI language models are by nature mysterious, but one can guess why ChatGPT responds this way. The bot smashes our questions into pieces and evaluates each for significance, looking for the crucial first bit that shapes the logical order of its response. It starts with a few letters or an entire word and barrel-rolls forward, predicting one word after another until eventually, it predicts that its answer should end. When asked about its abilities, ChatGPT seems to be keying in on its identity as the essential idea from which its ensuing chain of reasoning must flow. I am an AI language model, it says, and this is what AI language models do.

But while ChatGPT may be keenly attuned to its own identity—it will tell you all day long that it is an AI language model—the software seems much less certain of what its identity means it can do.  Indeed, whether you're asking about tasks that it can easily compute or those at the speculative edge of its abilities, you may end up with some very shaky answers.

To be fair, keeping up with AI language models would be tough for anyone. When OpenAI debuted the earliest version of GPT in June 2018, it was little more than a proof of concept. Its successor, released on Valentine's Day the following year, worked better, but it wasn't a polished interlocutor like the AIs we're accustomed to interacting with today. GPT-2 did a poorer job of summarizing blocks of text; it was a shoddier writer of sentences, let alone paragraphs.

[Read: GPT-4 has the memory of a goldfish]

In May 2020, GPT-3 was introduced to the world, and those who were paying close attention immediately recognized it as a marvel. Not only could it write lucid paragraphs, but it also had emergent capabilities that its engineers had not necessarily foreseen. The AI had somehow learned arithmetic, along with other, higher mathematics; it could translate between many languages and generate functional code.

Despite these impressive—and unanticipated—new skills, GPT-3 did not initially attract much fanfare, in part because the internet was preoccupied. (The model was released during the coronavirus pandemic's early months, and only a few days after George Floyd was killed.) Apart from a few notices on niche tech sites, there wasn't much writing about GPT-3 that year. Few people had even heard of it before November, when the public at large started using its brand-new interface: ChatGPT.

When OpenAI debuted GPT-4 two weeks ago, things had changed. The launch event was a first-rate tech-industry spectacle, as anticipated as a Steve Jobs iPhone reveal. OpenAI's president, Greg Brockman, beamed like a proud parent while boasting about GPT-4's standardized-test scores, but the big news was that the model could now work fluently with words and images. It could examine a Hubble Space Telescope image and identify the specific astrophysical phenomena responsible for tiny smudges of light. During Brockman's presentation, the bot coded up a website in seconds, based on nothing more than a crude sketch.

Nearly every day since fall, wild new claims about language models' abilities have appeared on the internet—some in Twitter threads by recovering crypto boosters, but others in proper academic venues. One paper published in February, which has not been peer-reviewed, purported to show that GPT-3.5 was able to imagine the interior mental states of characters in imagined scenarios. (In one test, for example, it was able to predict someone's inability to guess what was inside of a mislabeled package.) Another group of researchers recently tried to replicate this experiment, but the model failed slightly tweaked versions of the tests.

A paper released last week made the still-bolder claim that GPT-4 is an early form of artificial general intelligence, or AGI. Among other "sparks of generality," the authors cited GPT-4's apparent ability to visualize the corridors and dead ends of a maze based solely on a text description. (According to stray notes left on the preprint server where the paper was posted, its original title had been "First Contact With an AGI System.") Not everyone was convinced. Many pointed out that the paper's authors are researchers at Microsoft, which has sunk more than $10 billion into OpenAI.

There is clearly no consensus yet about the higher cognitive abilities of AI language models. It would be nice if the debate could be resolved with a simple conversation; after all, if you're wondering whether something has a mind, one useful thing you can do is ask it if it has a mind. Scientists have long wished to interrogate whales, elephants, and chimps about their mental states, precisely because self-reports are thought to be the least bad evidence for higher cognition. These interviews have proved impractical, because although some animals understand a handful of human words, and a few can mimic our speech, none have mastered our language. GPT-4 has mastered our language, and for a fee, it is extremely available for questioning. But if we ask it about the upper limit of its cognitive range, we're going to get—at best—a dated response.

[Read: Welcome to the big blur]

The newest version of ChatGPT won't be able to tell us about GPT-4's emergent abilities, even though it runs on GPT-4. The data used to train it—books, scientific papers, web articles—do include ample material about AI language models, but only old material about previous models. None of the hundreds of billions of words it ingested during its epic, months-long training sessions were written after the new model's release. The AI doesn't even know about its new, hard-coded abilities: When I asked whether GPT-4 could process images, in reference to the much-celebrated trick from its launch event, the AI language reminded me that it is an AI language model and then noted that, as such, it could not be expected "to process or analyze images directly." When I mentioned this limited self-appraisal on our AI Slack at The Atlantic, my colleague Caroline Mimbs Nyce described ChatGPT as having "accidental impostor syndrome."

To the AI's credit, it is aware of the problem. It knows that it is like Narcissus staring into a pond, hoping to catch a glimpse of itself, except the pond has been neglected and covered over by algae. "My knowledge and understanding of my own capabilities are indeed limited by my training data, which only includes information up until September 2021," ChatGPT told me, after the usual preamble. "Since I am an AI model, I lack self-awareness and introspective abilities that would enable me to discover my own emergent capabilities."

I appreciated the candor about its training data, but on this last point, I'm not sure we can take the bot at its word. If we want to determine whether it's capable of introspection, or other human-style thinking, or something more advanced still, we can't trust it to tell us. We have to catch it in the act.

 
 
 
My 6-Year-Old Son Died. Then the Anti-vaxxers Found Out.
 
 
 
 

My 6-year-old boy died in January. We lost him after a household accident, one likely brought on by a rare cerebral-swelling condition. Paramedics got his heart beating, but it was too late to save his brain. I could hold his hand, look at the small birthmark on it, comb his hair, and call out for him, but if he could hear me or feel me, he gave no sign. He had been a child in perpetual motion, but now we couldn't get him to wiggle a finger.

My grief is profound, ragged, desperate. I cannot imagine how anything could feel worse.

But vaccine opponents on the internet, who somehow assumed that a COVID shot was responsible for my son's death, thought my family's pain was funny. "Lol. Yay for the jab. Right? Right?" wrote one person on Twitter. "Your decision to vaccinate your son resulted in his death," wrote another. "This is all on YOU." "Murder in the first."

[Read: Twitter has no answers for #DiedSuddenly]

I'm a North Carolina–based journalist who specializes in countering misinformation on social media. I know that Twitter, Facebook, and other networks amplify bad information; that their algorithms feed on anger and division; that anonymity and distance bring out the worst in some people online. And yet I had never anticipated that anyone would mock and terrorize a grieving parent. I've now received thousands of harassing posts. Some people emailed me at work.

For the record, my son saw some of the finest pediatric-ICU doctors in the world. He was in fact vaccinated against COVID-19. None of his doctors deemed that relevant to his medical condition. They likened his death to a lightning strike.

Strangers online saw in our story a conspiracy—a cover-up of childhood fatalities caused by COVID vaccines, a ploy to protect Big Pharma.

To them, what happened to my son was not a tragedy. It was karma for suckered parents like me.

Although some abusive posts showed up on my public Facebook page, the problem started on Twitter—whose new CEO, Elon Musk, gutted the platform's content-moderation team after taking over.

I posted my son's obituary there because we'd started a fundraiser in his name for the arts program at his neighborhood school. Books didn't hold his interest, but he loved drawing big, blocky Where the Wild Things Are–style creatures. The fundraiser gave us something, anything, to do. Most people were kind. Many donated. But within days, anti-vaxxers hijacked the conversation, overwhelming my feed. "Billy you killed your kid man," one person wrote.

Accompanying the obituary was a picture of him showing off his new University of North Carolina basketball jersey—No. 1, Leaky Black—before a game. He's all arms and legs. He will only ever always be that. Cheeks like an apple. His bangs flopped over his almond-shaped eyes. "Freckles like constellations," his obit read. He looks unpretentious, shy, and bored. Like most children his age, anything that takes more than an hour, such as a college basketball game, is too long.  

Strangers swiped the photo from Twitter and wrote vile things on it. They'd mined my tweets, especially ones where I had written about the public-health benefits of vaccination. Someone needed to make me pay for vaccinating my child, one person insinuated. Another said my other children would be next if they were vaccinated too.

I tried to push back. Please take the conspiracy theories elsewhere, I pleaded on Twitter. That made things worse, so I stopped engaging. A blogger mocked me for fleeing social media. Commenters joined in. My grief, their content. "Your one job as a parent was to protect your children," wrote one person. "You failed miserably."

Our family's therapist distinguishes "clean grief" from "dirty grief." Clean grief is pure sadness. Dirty grief is guilt and what-ifs.

I can't fathom clean grief when you lose a healthy child so suddenly. But my doubts aren't about vaccination. I am filled with other questions. Had we missed earlier signs of illness? But also: Did he like me? What would he have been like as a teenager? Did he ever have a crush?

At first, I kept the harassment to myself. I didn't want my family to know. I worried that my sadness—the sadness that I owed my son—would be crowded out by anger. So I leaned into distractions: the people crammed into my living room, sitting on the floor and sifting through my records. Grubhub coupons. Friends washing our dishes. Cheesy baked spaghetti with cooking instructions taped to the foil. Better coffee than the swill I usually buy. Meg Ryan comedies. Lots of wine. Kids—mine, nephews, nieces, neighbors—everywhere. Brave bursts of laughter. Like a weird party for the worst thing that's ever happened to me.

[Jon D. Lee: The utter familiarity of even the strangest vaccine conspiracy theories]

I also remember the ping of my phone notifications. When our friends and relatives left at night, the pings kept coming from these strange ghouls on the internet. I wished that I believed in hell so I could imagine them going there. Losing a child is a brutal reminder that nothing is fair in this world. The harassment made me feel like there was nothing good in it either.

Some of the messages may have come from bots. Others appeared to be written by real people, including a guy whose email address identified the flooring company he owned in Alaska. "You killed your own son?" he wrote in the subject line. "You're an idiot." Do his family and friends know that he does this for kicks?

I'm not the only parent being harassed in this way. Some of the trolls posted photos of other children, insinuating that they had died because of COVID vaccines. I feel for the grieving mothers and fathers who receive those messages.

My friends and I reported some of the worst posts to Facebook and Twitter. A few users were booted from Twitter. But in most cases, we got no response; in a few, we received tepid form messages.

"Billy, we reviewed the comment you reported and found that it doesn't go against our Community Standards," Facebook told me after a stranger wormed their way onto an old post from my personal page to mock me. If I was offended, I could block them, the company said. Facebook might feel conflicted about whether to censor nipples, but tormenting a bereaved parent gets a pass.

Social-media companies will have to make a choice about the kind of space they want to create. Is it a space to connect, as Facebook solemnly promised in one 2020 commercial? Or is it a space where the worst behavior imaginable is not only tolerated but amplified?

In truth, although the cruelty of these strangers shocked me, they feel distant—like cats wailing in the alley. I can shut the window and ignore them. Nothing they say or do can fill the space he still takes up. I can smell him on his favorite blue blanket. I can feel him when I squeeze the bouncy balls that he hid, like treasure, in a wooden box by his bed. I can see him in the muddy Crocs that he left behind in one of the backyard nooks he liked to hide in. His absence feels impossible. I keep waiting for him to come back.

I can imagine my son asking, with characteristic bluntness, whether the people being mean to me on social media are good guys or bad guys, like in the movies. I probably would have reassured him that none of the messages I received was really about him. They were just a reflection of some people's desire to spread lies, and of the callous way we treat one another online. The messages don't affect how I choose to remember my boy.

In the last picture I have of him, taken five days before we lost him, he's getting a bad haircut at a kids' salon. The barber's chair looks like a miniature Batmobile, and his legs are folded up inside. He was tall for his age, as I once was. He was already pretty like his mom. In the picture, he's watching Paw Patrol on a little monitor placed strategically in front of the chair to keep the kids straight and still. He's old for the show, but he's too nice or shy to say so.

In the ICU, as we prepared to say goodbye to our son, my wife borrowed a pair of scissors from the nurse. And, being careful not to lay on any tubes going into and out of him, she crawled into his bed and straightened his bangs.

 
 
 
 
 

Nature Communications, Published online: 28 March 2023; doi:10.1038/s41467-023-37109-4

Cryo-EM structures of Ty1 integrase-Pol III complexes reveal determinants of Ty1 targeting upstream of Pol III-transcribed genes, and a functional impact of the integrase on Pol III activity that may increase the probability of Ty1 integration.
 
 
 
 
Is this article about Neuroscience?
 

Nature Communications, Published online: 28 March 2023; doi:10.1038/s41467-023-37213-5

Primary biliary cholangitis
 is a rare, chronic immune-mediated 
liver disease
 triggered by environmental exposures in genetically susceptible individuals. Here, the authors investigate the functional mechanism underlying the association of 19p13.3 variants with primary biliary cholangitis.
 
 
 
Fuel cell prototype runs on blood sugar
 
 
 
Is this article about Energy?
 
fabric-wrapped, square object held between gloved fingers
 
 

Researchers have developed an implantable fuel cell that uses excess blood sugar from tissue to generate electrical energy.

The researchers combined the fuel cell with artificial beta cells that produce insulin at the touch of a button and effectively lower blood glucose levels much like their natural role models in the pancreas.

In type 1 diabetes, the body does not produce insulin. This means that patients have to obtain the hormone externally to regulate their blood sugar levels. Nowadays, this is mostly done via insulin pumps that attach directly to the body. These devices, as well as other medical applications such as pacemakers, require a reliable energy supply, which primarily comes from single-use or rechargeable batteries.

"Many people, especially in the Western industrialized nations, consume more carbohydrates than they need in everyday life," says Martin Fussenegger, professor of biotechnology and bioengineering at ETH Zurich. This, he adds, leads to obesity, diabetes, and cardiovascular disease. "This gave us the idea of using this excess metabolic energy to produce electricity to power biomedical devices," he says.

"The new system autonomously regulates insulin and blood glucose levels and could be used to treat diabetes in the future."

At the heart of the fuel cell is an anode (electrode) made of copper-based nanoparticles, which Fussenegger's team created specifically for this application. It consists of copper-based nanoparticles and splits glucose into gluconic acid and a proton to generate electricity, which sets an electric circuit in motion.

Wrapped in a nonwoven fabric and coated with alginate, an algae product approved for medical use, the fuel cell resembles a small tea bag that can be implanted under the skin. The alginate soaks up body fluid and allows glucose to pass from the tissue into the fuel cell within.

In a second step, the researchers coupled the fuel cell with a capsule containing artificial beta cells. These can be stimulated to produce and secrete insulin using electric current or blue LED light. Fussenegger and his colleagues already tested such designer cells some time ago.

The system combines sustained power generation and controlled insulin delivery. As soon as the fuel cell registers excess glucose, it starts to generate power. This electrical energy is then used to stimulate the cells to produce and release insulin into the blood. As a result, blood sugar dips to a normal level. Once it falls below a certain threshold value, the production of electricity and insulin stops.

The electrical energy provided by the fuel cell is sufficient not only to stimulate the designer cells but also to enable the implanted system to communicate with external devices such as a smartphone. This allows potential users to adjust the system via a corresponding app. A doctor could also access it remotely and make adjustments.

"The new system autonomously regulates insulin and blood glucose levels and could be used to treat diabetes in the future," Fussenegger says.

The existing system is only a prototype. Although the researchers have successfully tested it in mice, they are unable to develop it into a marketable product. "Bringing such a device to market is far beyond our financial and human resources," Fussenegger says. This would call for an industry partner with the appropriate resources and know-how.

The study appears in Advanced Materials.

Source: ETH Zurich

The post Fuel cell prototype runs on blood sugar appeared first on Futurity.

 
 
 
Bangladesh bans plastics in world's largest mangrove forest
 
 
 
Feedly AI found 1 Regulatory Changes mention in this article
  • Bangladesh bans plastics in world's largest mangrove forest
 
Conservationists in Bangladesh said Tuesday that tourists dropping rubbish in the world's largest mangrove forest had seriously damaged the ecosystem, forcing the imposition of a single-use plastic ban in the World Heritage site.
 
 
 
Mice With Two Dads Were Born From Eggs Made Out of Male Skin Cells
 
 
 
Is this article about Pharma?
 

Seven mice just joined the pantheon of offspring created from same-sex parents—and opened the door to offspring born from a single parent.

In a study published in Nature, researchers described how they scraped skin cells from the tails of male mice and used them to create functional egg cells. When fertilized with sperm and transplanted into a surrogate, the embryos gave rise to healthy pups, which grew up and had babies of their own.

The study is the latest in a decade-long attempt to rewrite reproduction. Egg meets sperm remains the dogma. What's at play is how the two halves are generated. Thanks to iPSC (induced pluripotent stem cell) technology, scientists have been able to bypass nature to engineer functional eggsreconstruct artificial ovaries, and give rise to healthy mice from two mothers. Yet no one has been able to crack the recipe of healthy offspring born from two dads.

Enter Dr. Katsuhiko Hayashi at Kyushu University, who has led the ambitious goal to engineer gametes—sperm and egg—outside the body. His solution came from a clever hack. When grown inside petri dishes, iPSC cells tend to lose bundles of their DNA, called chromosomes. Normally, this is a massive headache because it disrupts the cell's genetic integrity.

Hayashi realized he could hijack the mechanism. Selecting for cells that shed the Y chromosome, the team nurtured the cells until they fully developed into mature egg cells. The cells—which started as male skin cells—eventually developed into normal mice after fertilization with normal sperm.

"Murakami and co-workers' protocol opens up new avenues in reproductive biology and fertility research," said Drs. Jonathan Bayerl and Diana Laird at the University of California, San Francisco (UCSF), who were not involved in the study.

Whether the strategy will work in humans remains to be seen. The success rate in mice was very low at just a snippet over one percent. Yet the study is a proof of concept that further pushes the boundaries of the reproductive realm of possibilities. And perhaps more immediately, the underlying technology can help tackle some of our most prevalent chromosomal disorders, such as Down syndrome.

"This is a very important breakthrough for the generation of eggs and sperm from stem cells," said Dr. Rod Mitchell at the MRC Centre for Reproductive Health, University of Edinburgh, who was not involved in the study.

A Reproductive Revolution

Hayashi is a long-time veteran at transforming reproductive technologies. In 2020, his team described genetic alterations that help cells mature into egg cells inside a dish. A year later, they reconstructed ovary cells that nurtured fertilized eggs into healthy mouse pups.

At the core of these technologies are iPSCs. Using a chemical bath, scientists can transform mature cells, such as skin cells, back into a stem-cell-like state. iPSCs are basically biological playdough: with a soup of chemical "kneading," they can be coaxed and fashioned into nearly any type of cell.

Because of their flexibility, iPSCs are also hard to control. Like most cells, they divide. But when kept inside a petri dish for too long, they rebel and either shed—or duplicate—some of their chromosomes. This teenage anarchy, called aneuploidy, is the bane of scientists' work when trying to keep a uniform population of cells.

But as the new study shows, that molecular rebellion is a gift for generating eggs from male cells.

X Meets Y and…Meets O?

Let's talk sex chromosomes.

Most people have either XX or XY. Both X and Y are chromosomes, which are large bundles of DNA—picture threads wrapped around a spool. Biologically, XX usually generates eggs, whereas XY normally produces sperm.

But here's the thing: scientists have long known that both type of cells start from the same stock. Dubbed primordial germ cells, or PGCs, these cells don't rely on either X or Y chromosomes, but rather on their surrounding chemical environment for their initial development, explained Bayerl and Laird.

In 2017, for example, Hayashi's team transformed embryonic stem cells into PGCs, which when mixed with fetal ovary or testes cells matured into either artificial eggs or sperm.

Here, the team took on the harder task of transforming an XY cell into an XX one. They started with a group of embryonic stem cells from mice that shed their Y chromosomes—a rare and controversial resource. Using a glow-in-the-dark tag that grabs only onto X chromosomes, they could monitor how many copies there were inside a cell based on light intensity (remember, XX will shine brighter than XY).

After growing the cells for eight rounds inside petri dishes, the team found that roughly six percent of the cells sporadically lost their Y chromosome. Rather than XY, they now only harbored one X—like missing half of a chopstick pair. The team then selectively coaxed these cells, dubbed XO, to divide.

The reason? Cells duplicate their chromosomes before splitting into two new ones. Because the cells only have one X chromosome, after duplication some of the daughter cells will end up with XX—in other words, biologically female. Adding a drug called reversine helped the process along, increasing the number of XX cells.

The team then tapped into their previous work. They converted XX cells into PGC-like cells—the ones that can develop into egg or sperm—and then added fetal ovary cells to push the transformed male skin cells into mature eggs.

As the ultimate test, they injected sperm from a normal mouse into the lab-made eggs. With the help of a female surrogate, the blue-sky experiment produced over a half-dozen pups. Their weights were similar to mice born the traditional way, and their surrogate mom developed a healthy placenta. All of the pups grew into adulthood and had babies of their own.

Pushing Boundaries

The tech is still in its early days. For one, its success rate is extremely low: only 7 out of 630 transferred embryos lived to be full-grown adults. With a mere 1.1 percent chance at succeeding—especially in mice—it's a tough sell for bringing the technology to male human couples. Although the baby mice seemed relatively normal in terms of weight and could reproduce, they could also harbor genetic or other deficiencies—something that the team wants to further investigate.

"There are big differences between a mouse and the human," said Hayashi at an earlier conference.

That said, reproduction aside, the study may immediately help to understand chromosomal disorders. Down syndrome, for example, is caused by an extra copy of chromosome 21. In the study, the team found that treating mouse embryonic stem cells harboring a similar defect with reversine—the drug that helps convert XY to XX cells—rid the mice of the extra copy without affecting other chromosomes. It's far from being ready for human use. However, the technology could help other scientists hunt down preventative or screening measures for similar chromosomal disorders.

But perhaps what's most intriguing is where the technology can take reproductive biology. In an audacious experiment, the team showed that cells from a single male iPSC line can birth offspring—pups that grew into adulthood.

With the help of surrogate mothers, "it also suggests that a single man could have a biological child…in the far future," said Dr. Tetsuya Ishii, a bioethicist at Hokkaido University. The work could also propel bioconservation, propagating endangered mammals from just a single male.

Hayashi is well aware of the ethics and social implications of his work. But for now, his focus is on helping people and deciphering—and rewriting—the rules of reproduction.

The study marks "a milestone in reproductive biology," said Bayerl and Laird.

Image Credit: Katsuhiko Hayashi, Osaka University

 
 
 
Tumor model clarifies how bone cancer defies chemo
 
 
 
 
gloved hand holds white disc in tweezers
 
 

A new upgraded model shows how the body's immune response can make tumor cells more resistant to chemotherapy.

Tumor cells won't show their true selves in a Petri dish, isolated from other cells. To find out how they really behave, researchers developed the new model that houses osteosarcoma cells beside immune cells known as macrophages inside a three-dimensional structure engineered to mimic bone.

The study, published in Biomaterials, sheds light on why some 

cancer

 drugs that appear to be good candidates in the lab do not perform as well as expected in actual patients. It underscores weaknesses in traditional tumor modeling and points the way toward more effective cancer therapies.

"Existing tumor models used to test drug performance do not mimic the actual environment in the human body closely enough," says Antonios Mikos, a professor of bioengineering and chemical and biomolecular engineering at Rice University.

"We are trying to create an environment for the experiment that is closer to what is happening in the organism of actual patients. Having such an environment will allow us to test multiple drugs in a time- and cost-effective way."

Mikos' lab had shown in previous work that cancer cells are sensitive to the mechanical properties of their substrate.

"Typically, cells would be grown on a flat surface, like in a Petri dish," says lead author Letitia Chim, who recently earned a doctorate at Rice. "If you use a microscope to look at the disc-shaped scaffolds we developed, you can see that they are made up of these fiber structures on the scale of what cells would recognize. The cells can sense that this substrate is three-dimensional instead of flat—closer to what bone structure is like."

The scaffolds are made from two different materials: a very stiff synthetic polymer and gelatin. By changing the ratio of the materials, researchers can control the overall stiffness of the fibers.

"What is new here and very revealing is that we added the next level of complexity—the immune cells that are part of the tumor microenvironment—and looked at how the combination of the mechanical responsiveness of the substrate and the presence of other cells factors into tumor development and behavior," Mikos says.

"In a tumor, you don't only have the cancer cells, you have other cells that are sending out signals that can affect how the cancer cells will respond to treatment," Chim says.

Researchers found that increased inflammation caused by macrophages reduced the effectiveness of doxorubicin, one of the chemotherapeutic agents used to treat osteosarcoma, which is the most common form of 

bone cancer

.

"We were interested in tumor-associated macrophages because they can make up to 50% of the tumor," Chim says. "Tumors have sometimes been described as wounds that never heal, and that's partly due to the macrophages sending out wound-healing signals. In normal tissue that works well, but it can also benefit the tumor."

Preclinical models that mimic tumors more accurately can help researchers identify which therapies are most effective in a given context.

"This is going to be useful in order to design therapeutics that target not only the cancer cells but also the immune cells, or that trigger the immune cells to essentially change their function," Mikos says.

"A major objective of our research is to develop personalized testing systems or platforms where the characteristics of the patient's tumor are used to find a therapeutic model that works best for them," Chim says. "I would say that's the personalized medicine vision of the future: being able to answer the question, are there particular targeted treatments that work well for this patient?

"Osteosarcoma is a rare disease that often gets overlooked. It's also a really complicated disease that shows up differently in every single patient. This is another reason why it would ultimately be great if we can develop a personalized medicine approach for treating osteosarcoma."

"The tumor microenvironment clearly plays an important role in how disease progression and treatment unfold," Mikos says. "That is why we strive to develop an optimal level of complexity that captures the bigger picture of what actually happens inside a live organism."

The National Institutes of Health funded the research.

Source: Rice University

The post Tumor model clarifies how bone cancer defies chemo appeared first on Futurity.

 
 
 
Smell-Loss Tests Could Reveal Health Problems
 
 
 
Feedly AI found 1 Participation in an Event mention in this article
  • The Monell Center, STANA and many other organizations are currently planning a conference to bring together scientists, clinicians, public health officials and people with smell and taste disorders to further workshop how to make universal chemosensory testing a reality.
 

Unlike other senses, smell is not something doctors routinely test for—but some scientists think that should change

 
 
 
New study finds toxic PFAS 'forever chemicals' in Canadian fast-food packaging
 
 
 
 
Researchers at the University of Toronto, Indiana University and University of Notre Dame have detected levels of toxic PFAS chemicals—short for per- and polyfluoroalkyl substances—for the first time in Canadian fast-food packaging, specifically water-and-grease repellent paper alternatives to plastic.