Category: Science & Technology

Google and Meta are clashing over kids’ online safety, blaming each other while evading responsibility.

The ongoing battle between Google and Meta over kids’ online safety has intensified, with both companies accusing each other of evading responsibility. Google recently called out Meta and other social media platforms for backing laws that shift the burden of age verification to app stores. Meanwhile, Meta argues that app stores should take more responsibility.
Google Slams Meta
Google’s criticism comes after Utah became the first U.S. state to pass legislation requiring app stores like the Google Play Store and Apple App Store to verify users’ ages and obtain parental consent before minors can download apps. While Meta, Snap, and X supported the new law, Google opposed it, calling it “concerning” and claiming it fails to address the actual risks children face online.
The company argues that the responsibility for age verification should fall on social media platforms, not app stores. Kareem Ghanem, Google’s public policy director, stated that the law allows platforms like Meta to escape accountability, despite being the primary space where children engage with online content.

Google’s Alternative Proposal
To counter Utah’s law, Google proposed its own framework, which suggests that age verification should only apply to specific apps deemed risky rather than all apps. It also wants app developers, not app stores, to determine what protections are necessary.

Critics argue that Google’s proposal is simply a way to avoid taking responsibility. By putting the decision in developers’ hands, Google creates a loophole that could allow unsafe apps to slip through the cracks. Apple, in its latest online safety report, raised concerns that this approach could lead to excessive data collection from children, as developers may ask for sensitive identification details to comply with regulations.
Meta Shifts Blame to App Stores
Meta, on the other hand, sees things differently. The company welcomed Google’s acknowledgement that app stores can share age data with developers but questioned how Google would decide which apps need this information. Meta argues that the easiest way to protect minors is to put parents in control by making app stores responsible for obtaining parental consent.

Source: https://www.timesnownews.com/technology-science/google-and-meta-play-the-blame-game-while-kids-online-safety-remains-at-risk-article-119032505

A SpaceX Falcon 9 rocket successfully lifted off from Florida on Friday with four crew on board. It means Butch Wilmore and Suni Williams can finally come home after their eight-day mission was extended to nine months because of technical problems.

A long-awaited rocket with a replacement crew for two stranded NASA astronauts has finally launched to the International Space Station (ISS).

US astronauts Butch Wilmore and Suni Williams have been stuck on the ISS for nine months, having had their journey home repeatedly pushed back.

The Crew-10 mission was initially scheduled to launch the replacement crew of four astronauts from Florida on Wednesday, but a last-minute issue with the rocket’s ground systems forced a delay.

NASA said on Thursday that SpaceX, headed and founded by tech billionaire Elon Musk, had resolved the issue – flushing a suspected pocket of air out of a hydraulic clamp arm – and that the weather was 95% favourable for a Friday launch.

The crew is now expected to arrive at the ISS on Saturday night. They are NASA’s Anne McClain and Nichole Ayers, who are both military pilots, along with Japan’s Takuya Onishi and Russia’s Kirill Peskov, both former airline pilots.

They will spend the next six months at the space station, releasing Mr Wilmore and Ms Williams who have been on the ISS since June 2024.

The pair originally planned to go to space for just eight days but got stuck on the station after their Boeing Starliner spacecraft started experiencing problems.

The mission has become entangled in politics as Donald Trump and his adviser Elon Musk claimed – without evidence – that former President Joe Biden left the astronauts on the station for political reasons.

NASA said the two astronauts have had to remain on the ISS to maintain its minimum staffing level.

Source: https://news.sky.com/story/rocket-with-replacement-crew-for-nasa-astronauts-stranded-for-nine-months-finally-launches-13328607

Spotify paid the music industry $10bn (£7.7bn) in 2024, which the streaming service said was the highest annual payment from any single retailer in history.

But the figures come as a heated debate continues about how much money artists and songwriters receive in royalties.

Earlier this year, several Grammy-nominated songwriters boycotted an awards event hosted by Spotify in a row about their streaming earnings.

As the new figures were published, a spokesperson for Spotify said the responsibility for distributing the money it pays lay with record labels and publishers.

The company said it pays royalties to rights holders, adding that it does not have “visibility” on where the money ultimately goes because earnings are based on artists’ individual contracts with their labels.

A spokesperson said: “Spotify does not pay artists or songwriters directly. We pay rights-holders, these are typically record labels, music publishers, collection societies.

“These rights-holders then pay artists and songwriters based on their individual agreements.”

The amount of money earned by artists will vary, but a committee of MPs heard in 2021 that the performer ultimately earns about 16% of a stream’s overall value.

That would mean an artist whose music generated £100,000 on Spotify might only receive £16,000 in royalty payments, before tax.

However, Spotify is not the only streaming service to generate revenue for artists, and many pop stars make more money from other income streams such as live tours.

Spotify said more than two-thirds of all music revenue goes “straight to the recording and publishing rights-holders”, and added that, like other streamers, Spotify does not pay on a per-stream basis.

The annual figures were published in Spotify’s Loud and Clear report – part of the company’s aim to provide transparency on how it pays the music industry.

The amount Spotify paid this year was an increase on the more than $9bn (£7bn) it handed over in 2023.

The report highlighted that the number of artists generating annual royalties between $1,000 (£770) and $10m had tripled since 2017.

Taylor Swift was named Spotify’s top artist globally with more than 26 billion streams, in the year she released her double-length album The Tortured Poets Department: The Anthology.

Swift herself was part of the debate about streaming royalties in 2014, when she removed her music from Spotify as part of a boycott, eventually re-joining the platform in 2017.

Source: https://www.bbc.com/news/articles/cy9d53rx7jxo

Look, we all know AI has both its advantages (e.g. offering convenient assistance, quick content, and sometimes reliable information) and disadvantages (e.g. stealing our jobs and potentially replacing humans altogether, but I digress).

However, one facet of AI that many people overlook is its impact on our cognitive abilities. A recent paper from researchers at Microsoft and Carnegie Mellon University explored this exact concern.

“Used improperly, technologies can and do result in the deterioration of cognitive faculties that ought to be preserved,” the paper states.

The researchers added that “by mechanizing routine tasks and leaving exception-handling to the human user, you deprive the user of the routine opportunities to practice their judgment and strengthen their cognitive musculature, leaving them atrophied and unprepared when the exceptions do arise.”

work harder, not smarter?

In today’s fast-paced world, it’s hard to even find the time to sit and enjoy a simple cup of coffee in the morning. Working smarter rather than harder feels like the only way to keep up and survive sometimes.

Of course, we can cut back on our social media consumption and doomscrolling, but utilizing the tools we have in front of us, like AI, is merely a form of adapting. For example, rather than going to a library and scouring multiple books, spending hours searching for information and resources on a specific topic, we can now access that information almost immediately on the Internet. Could you imagine if that was never an option? I’d rather not.

Just because technology is convenient doesn’t necessarily mean it’s bad. However, we do want to acknowledge the impact that it has on our brains and our cognitive abilities. This is especially true when it comes to generative AI, which is arguably the most concerning tech development in recent years.

The paper concluded: “While GenAI can improve worker efficiency, it can inhibit critical engagement with work and can potentially lead to long-term overreliance on the tool and diminished skill for independent problem-solving.”

Additionally, “Higher confidence in GenAI’s ability to perform a task is related to less critical thinking effort. When using GenAI tools, the effort invested in critical thinking shifts from information gathering to information verification; from problem-solving to AI response integration; and from task execution to task stewardship.”

This removes a bulk of our mind’s “dirty work,” so to speak—but is it forming a lazy habit for our brains?

AI could Be Making You Dumb, But That Might Be the Least of Your Worries

One can argue that outsourcing certain parts of our mental workload allows us to invest more energy into other things, like our creativity or emotional intelligence. However, overreliance on such technologies can, of course, have adverse effects.

The researchers concluded that their work “suggests that GenAI tools need to be designed to support knowledge workers’ critical thinking by addressing their awareness, motivation, and ability barriers.”

Look, if the world suddenly went totally off the grid and we had zero access to the Internet, we can pretty much guarantee we’d all be fucked—at least here in the US. But to be honest, our declining mental cognitive habits are really the least of our worries.

Source : https://www.vice.com/en/article/ai-makes-you-lazy-and-stupid-if-you-let-it/

Artificial intelligence (AI) has undergone a massive transformation over the past decade, evolving from narrow applications in machine vision and predictive modelling to the more complex and versatile world of generative AI (GenAI). The recent popularity of OpenAI’s ChatGPT and the emergence of similar GenAI models since then, has made this space more competitive.
Leading this shift is Nagarro, a global product engineering company that has been at the forefront of AI innovation. In conversations with Anurag Sahay, MD and Head of Data and AI at Nagarro, and Ananda Sengupta, MD, Head of Telecom at the company, we explored how Nagarro is differentiating itself in the competitive AI landscape, tackling challenges, and ensuring responsible AI development.

Ice could be present at more locations right beneath the Moon’s surface at the poles than previously thought, a study of data collected by the Chandrayaan-3 mission has suggested.

Large, yet highly local, changes in surface temperatures can directly affect the forming of ice, and looking into these ice particles can reveal “different stories about their origin and history”, lead author, Durga Prasad Karanam, Faculty, Physical Research Laboratory, Ahmedabad told PTI.

This can also tell us about how ice accumulated and moved through the Moon’s surface over time, which can provide insights into the natural satellite’s early geologic processes, he said. The findings are published in the journal Communications Earth and Environment.

The Chandrayaan-3 mission, launched by the Indian Space Research Organisation (ISRO) from Bengaluru, achieved a soft landing near the Moon’s south pole on August 23, 2023. The landing site was named the ‘Shiv Shakti Point’ three days later on August 26.

For this study, the researchers analysed temperatures measured at and to a depth of 10 centimetres beneath the lunar surface. Measurements were taken by the ‘ChaSTE’ probe on-board the Chandrayaan-3’s Vikram lander.

The lander touched down at the edge of the Moon’s south pole region, about 69 degrees south latitude.

At this landing site — “a Sun-facing slope angled at six degrees” — the authors found that temperatures peaked at about 82 degrees Celsius and dropped to -170 degrees Celsius in the night.

However, barely a metre away from the landing point — a flat surface — temperatures peaked at about 60 degrees Celsius.

“That slight slope resulted in an increased solar radiation at the ChaSTE penetration point,” Karanam said.

Further, the team developed a model of how slope angle can affect surface temperature at a high lunar latitude, such as the latitude of the landing site.

The model indicated that, for slopes facing away from the Sun and towards the Moon’s nearest pole, a slope inclined at an angle greater than 14 degrees may be cool enough for ice to accumulate close to the surface.

The slope conditions suggested by the model were found to be similar to those of landing points, proposed for NASA’s manned mission to the Moon’s south pole — the ‘Artemis’.

The authors, therefore, suggested that potentially, there could be multiple places on the Moon where ice can form and be accessed more easily than previously thought.

In response to PTI’s question on the chances of ice turning into water on the Moon, Karanam said, “Water in liquid form cannot exist on the lunar surface because of (an) ultra-high vacuum. Therefore, ice cannot transform into liquid, but would rather sublimate to vapour form.” “As of the present understanding, Moon might not have had habitable conditions in the past,” Karanam said.

However, ice is a potential resource for future on-site exploration and habitability of the Moon, and that more measurements, such as those from ChaSTE, are needed to gain a comprehensive picture, he added.

“Techniques and strategies need to be developed for extraction and usage of ice for long term sustainability on the Moon,” the lead author said.

Source : https://www.ndtv.com/science/chandrayaan-3-data-suggests-says-ice-may-exist-on-moon-at-more-locations-than-previously-thought-7864373

When someone loses a hand, today’s prosthetic options force painful compromises. Rigid prosthetics offer strength but can’t handle delicate objects gently. Soft robotic alternatives provide gentleness but lack gripping power. And neither option lets users actually feel what they’re touching.

We’ve all been there. You’re in a meeting, your phone buzzes with an Instagram notification, and suddenly your fingers itch to check it. But what’s actually happening inside your body during that moment of craving? A new study from Durham University has finally mapped the physiological rollercoaster we experience during those quick Instagram checks—and more importantly, what happens when we’re forced to resist the urge to scroll.

Checking social media has become engrained in the daily routines of billions worldwide. Despite the ubiquity of this behavior, surprisingly little was known about its immediate impact on our bodies and minds until now. Unlike previous research focusing on internet use broadly, this investigation zeroed in specifically on Instagram—one of the most visually-oriented and popular platforms among young adults.

Dr. Michael Wadsley and Dr. Niklas Ihssen’s study, titled “The psychophysiology of Instagram,” tracked what happens inside our bodies during typical Instagram sessions and subsequent periods when usage is halted. Their findings reveal a troubling pattern: brief Instagram engagement triggers reward-based arousal and deep attentional immersion, while stopping triggers stress responses—regardless of whether someone exhibits problematic social media habits or not.

In a commentary on The Conversation, Dr. Ihssen himself explains the significance: “What we found was that, relative to the news reading condition, scrolling away on Instagram led to a marked slowing of participants’ heart rate while, at the same time, increasing their sweating response.” He adds, “From other research we know that such a pattern of bodily responses shows that someone’s attention is fully absorbed by a highly significant or emotional stimulus in their environment – it’s a state of simultaneous excitement and deep immersion into something very meaningful to us.”

Instagram’s Insta-effects

The research team monitored heart rate, skin conductance (which measures emotional arousal through tiny changes in sweat gland activity), and subjective feelings across three 15-minute phases with 54 Instagram users. Participants first completed a baseline reading phase, followed by an Instagram browsing phase, and finally a phase where they were forced to stop using Instagram while receiving notifications.

During Instagram use, participants experienced a significant decrease in heart rate compared to baseline—a sign of deep attentional focus similar to what happens when we’re completely absorbed in a task. This heart rate slowdown occurred alongside increased skin conductance, indicating heightened pleasurable arousal—essentially, the reward center of the brain activating.

This combination reveals users enter a distinctive mental state characterized by profound immersive engagement while simultaneously experiencing heightened arousal—a potent mixture that likely contributes to social media’s powerful appeal.

“Importantly, from the control condition we knew that it was not just being on the phone or reading that caused this bodily response,” writes Dr. Ihssen. “So there seems to be something special about social media that can easily engross us.”

What Happens When We Stop Scrolling?

Perhaps most revealing was the body’s response when participants were forced to stop using Instagram, especially while receiving notifications they couldn’t check. Heart rates increased, skin conductance readings climbed even higher, and participants reported significant increases in stress, anxiety, and social media cravings.

“The most intriguing effect in our study happened when we interrupted participants at the end of their Instagram stint and asked them to go back to reading another news article,” Dr. Ihssen explains in his Conversation post. “Rather than snapping out of the excitement and returning to a calmer state, participants’ sweating response increased further, while heart rate also increased rather than slowed down further.”

These bodily changes paint a picture of what might be happening inside billions of people multiple times throughout their day: cycles of immersion, reward, and subsequent stress when usage stops. The fact that these responses occurred regardless of whether someone scored high or low on problematic social media use measures raises important questions about how these platforms affect us all.

What makes social media so compelling isn’t just its addictive design features but something more fundamental to human nature. “Our previous study shows that it is primarily the social aspect of social media that drives most people to use it so intensively,” writes Ihssen. “This also means that – in contrast to drugs – social media taps into basic human needs: we all want to belong and to be liked. So if we recognize the existence of ‘social media addiction’, we might also need to recognize a ‘friendship addiction.’”

Beyond ‘Addiction’: A Universal Response

With more parents, educators, doctors, and users themselves becoming aware of the impacts from social media “addiction,” this research offers valuable physiological evidence of its power. While stopping short of confirming social media addiction as a formal diagnosis (none currently exists), the study demonstrates that even brief social media sessions trigger measurable changes in our bodies similar to patterns seen in reward-seeking behaviors.

The discovery that Instagram usage creates a state comparable to what psychologists call “motivated attention”—a heightened focus toward emotionally significant information—helps explain why scrolling through Instagram can feel so absorbing. The platform delivers an endless stream of novel, emotionally significant, and personally relevant content—perfect for continuously capturing our attention.

The Stress-Relief Paradox

Interestingly, previous research found that using social media before or after stressful events can actually buffer physiological stress responses. The heart rate deceleration observed during Instagram use in this study helps explain this phenomenon—social media may temporarily induce a state of attentional immersion that counteracts stress-related physiological arousal.

However, this comes with a significant downside: when usage stops, users experience this powerful rebound of stress-related physiological activation and subjective distress. This creates a potentially problematic cycle—social media temporarily reduces stress, but stopping usage increases it, potentially driving people back to the platform for relief.

Most concerning are the implications for the billions of brief social media sessions occurring worldwide each day. If each session involves cycles of reward-driven immersion followed by stress when usage stops, we might be subjecting ourselves to numerous micro-cycles of physiological and psychological stress daily.

For the average Instagram user who checks the app ten times daily, this could mean ten daily cycles of immersion and withdrawal—each one potentially contributing to accumulated stress. Moreover, if each cycle reinforces the association between Instagram use and stress relief, it could strengthen habitual usage patterns over time.

Engineered for Engagement

The research methodology cleverly mimicked natural usage patterns by examining brief 15-minute windows—much closer to how people actually use these platforms in everyday life, with the average session lasting 10-20 minutes.

Even more ingenious was the cessation phase design, where participants received notifications on their phones but were prohibited from checking them—a common real-world scenario many people experience during meetings, classes, or other situations where checking social media is inappropriate or impossible.

A picture emerges of social media platforms expertly designed to exploit fundamental attentional and reward mechanisms in the human brain. The content—friends’ photos, entertaining videos, personally relevant information—naturally triggers attention and reward anticipation, creating a deeply immersive experience that temporarily reduces stress.

Source : https://studyfinds.org/what-happens-to-your-body-during-an-instagram-session/

Scientists trying to bring back the woolly mammoth have created a woolly mouse.

Colossal Biosciences unveiled plans in 2021 to revive the woolly mammoth – and later the dodo bird – attracting investors, headlines and critics alike.

The Texas-based biotech company has since focused on identifying the key traits of extinct animals with the goal of genetically engineering them into living animals, according to chief executive Ben Lamm.

Alongside bringing back species that went extinct, the company hopes their work can be used to help with conservation efforts.

But other scientists have mixed views of their work and whether it will be helpful.

On Tuesday, Colossal Biosciences said its researchers had edited seven genes in mice embryos to create a mouse with long, thick, woolly hair.

They nicknamed the extra-furry rodent a “colossal woolly mouse.”

The company now plans to genetically modify Asian elephants to give them woolly mammoth traits – but critics have argued that this is different from actually bringing a species back from extinction.

“You’re not actually resurrecting anything – you’re not bringing back the ancient past,” said Christopher Preston, a wildlife and environment expert at the University of Montana, who was not involved in the research.

He added: “You might be able to alter the hair pattern of an Asian elephant or adapt it to the cold, but it’s not bringing back a woolly mammoth. It’s changing an Asian elephant.”

The results have not yet been published in a journal or vetted by independent scientists.

The feat “is technologically pretty cool,” said Vincent Lynch, a biologist at the University of Buffalo, who was not involved in the research.

Alongside the mouse being given different hair, in a press release, Colossal Biosciences said the rodent had also gained the woolly mammoth’s accelerated fat metabolism.

Both were said to be likely related to cold tolerance.

These genetic variations were already present in some living mice, the company’s chief scientist Beth Shapiro said, adding: “We put them all together in a single mouse.”

Source : https://news.sky.com/story/scientists-trying-to-bring-back-woolly-mammoth-create-a-woolly-mouse-13321512

Computers are hungry beasts. They devour vast amounts of power, especially when writing data to memory—a process that traditionally uses electric currents and generates wasteful heat. But what if we could control magnetic information storage with voltage instead? This approach is gaining traction as researchers seek more energy-efficient computing solutions for our data-hungry world.

In a paper published in Nature Communications, researchers from The Autonomous University of Barcelona have unveiled a novel nanoscale magnetic state they’ve dubbed a “vortion” (short for magneto-ionic vortex). This innovative approach uses voltage-controlled ion movement to create and manipulate swirling magnetic patterns at the nanoscale, potentially transforming how computers store and process information.

“This is a so far unexplored object at the nanoscale,” explains Jordi Sort, an ICREA researcher in the UAB Department of Physics and director of the research, in a statement. “There is a great demand for controlling magnetic states at the nanoscale but, surprisingly, most of the research in magneto-ionics has so far focused on the study of films of continuous materials. If we look at the effects of ion displacement in discrete structures of nanometer dimensions, the ‘nanodots’ we have analyzed, we see that very interesting dynamically evolving spin configurations appear, which are unique to these types of structures.”

The research team, led by scientists from Universitat Autònoma de Barcelona, has discovered a way to precisely control the magnetic properties of tiny dots of metal with extremely low power consumption. Their method allows for continuous, analog adjustment of magnetization—similar to turning a dimmer switch rather than flipping a binary on/off toggle—opening exciting possibilities for brain-inspired computing technologies.

How Vortions Work

At the heart of this innovation is a clever manipulation of nitrogen ions within specially engineered iron-cobalt-nitrogen (FeCoN) nanomagnets. By applying voltage, researchers can extract nitrogen ions from these tiny dots, transforming them from magnetically inert to magnetically active in controlled, gradual ways. This creates distinctive swirling magnetic patterns—vortices that can be precisely tuned and manipulated.

“With the ‘vortions’ we developed, we can have unprecedented control of magnetic properties such as magnetization, coercivity, remanence, anisotropy or the critical fields at which vortions are formed or annihilated. These are fundamental properties for storing information in magnetic memories, which we are now able to control and tune in an analog and reversible manner by a voltage-activated process with very low energy consumption,” explains Irena Spasojević, postdoctoral researcher in the UAB Department of Physics and first author of the paper.

Unlike traditional magnetic vortices, which are typically fixed in their properties once manufactured, these voltage-controlled vortions offer unprecedented flexibility. Their magnetic strength, stability, and behavior can all be adjusted after fabrication, eliminating the need for energy-intensive techniques like laser pulses or electrical currents to manipulate magnetic states.

“The voltage actuation procedure, instead of using electric current, prevents heating in devices such as laptops, servers and data centers, and it drastically reduces energy loss,” Spasojević adds.

The Brain-Computer Connection

Traditional computing relies on binary states—ones and zeros—but the human brain processes information in a much more nuanced, analog fashion with varying connection strengths between neurons. This new technology moves closer to brain-like computing by enabling analog states with continuous degrees of magnetization that can be adjusted with voltage, potentially leading to more efficient and sophisticated computing architectures.

By controlling how long voltage is applied, researchers can precisely adjust the thickness of the ferromagnetic layer, enabling transitions between different magnetic states—from nonmagnetic to single-domain to vortex states.

Researchers have shown that by precisely controlling the thickness of the voltage-generated magnetic layer, the magnetic state of the material can be varied at will, in a controlled and reversible manner, between a non-magnetic state, a state with a uniform magnetic orientation (such as that found in a magnet), and the new magneto-ionic vortex state.

From Lab to Applications

“We envision, for example, the integration of reconfigurable magneto-ionic vortices in neural networks as dynamic synapses, capable of mimicking the behavior of biological synapses,” Sort explains.

In the brain, the connections between neurons, the synapses, have different weights (intensities) that adapt dynamically according to the activity and learning process. Similarly, “vortions” could provide tuneable neuronal synaptic weights, reflected in reconfigurable magnetization or anisotropy values, for brain-inspired spintronic devices.

“The activity of biological neurons and synapses is also controlled by electrical signals and ion migration, analogous to our magneto-ionic units,” says Spasojević.

In current neuromorphic systems, one challenging aspect is creating and adjusting synaptic weights—the strength of connections between artificial neurons. Vortions could serve this function, with their magnetization strength controlled by voltage to represent different connection strengths.

The energy efficiency of this approach is particularly noteworthy. Conventional methods for manipulating magnetic states often require substantial energy input through electrical currents or laser pulses. The voltage-based control of vortions consumes minimal power, aligning with the urgent need to reduce energy consumption in information technologies as data processing demands continue to grow.

Researchers believe that, besides their impact in brain-inspired devices, analog computing or multi-state data storage systems, vortions may have other potential applications, including medical therapy techniques, data security, magnetic spin computing devices, and the generation of spin waves.

In a world increasingly dominated by data-hungry technologies from artificial intelligence to the Internet of Things, innovations that increase computational efficiency while reducing energy consumption have never been more important. Voltage-controlled vortions may soon join the arsenal of technologies helping to meet these challenges, swirling their way into the future of computing with an energy-efficient spin.

Source : https://studyfinds.org/new-magnetic-state-vortions/

Of course, we all need to be concerned about young people’s exposure to social media, and recent research adds another concern – a link to eating disorders.

A study published in Eating and Weight Disorders in September 2024 found that each additional hour of total screen time and social media use was associated with a greater incidence of fear of weight gain and self-worth tied to weight. Data came from more than 10,000 children, aged 9 to 14 years. With increases in screen time, the participants also showed increases in compensatory behaviors to prevent weight gain (such as compulsive over-exercising), binge eating, and distress with binge eating two years later. Both problematic social media and mobile phone use were associated with higher odds of all eating disorder symptoms.

The scientists concluded that greater total screen time, social media use, and problematic screen use are associated with more eating disorder symptoms in early adolescence. They suggested that healthcare providers consider assessing children for problematic levels of screen use, and for disordered eating with high screen use.

It shouldn’t be construed from these results that this concerning association between screen time and disordered eating is isolated to 9- to 14-year-olds. That’s simply the age group covered in this study.

An increase in screen time has also been linked to an increase in being the recipient of cyberbullying. A study in the International Journal of Eating Disorders, September 2023, showed cyberbullying victimization was also associated with worry about weight gain, self-worth tied to weight, inappropriate compensatory behavior to prevent weight gain, and distress with binge eating. Interestingly, the perpetrators of cyberbullying had the same associations with the same unhealthy behaviors.

This study involved the same group of children as the 2024 study, with the ages limited to 10—to 14-year-olds. The scientists also suggested that healthcare providers consider assessing for cyberbullying and eating disorder symptoms in early adolescence and providing anticipatory guidance to parents and adolescents.

Binge-watching and binge-scrolling may also influence binge eating, according to Dr. Jason Nagata, an associate professor of pediatrics at the University of California—San Francisco. His 2021 study in the International Journal of Eating Disorders showed that each additional hour of screen time per day was associated with higher odds of binge-eating disorder one year later. Data was collected on more than 11,000 children between the ages of 9 and 10.

What’s the connection?

The strong connection between social media and eating disorders is multifactorial, including comparisons, exposure to impossible body ideals, and the constant repetition of compulsive behaviors. It exposes teens to greater numbers of different ideas. That can be both good and bad. Obviously, not everyone has healthy ideas about food and body image. They can share dangerous behaviors and those can start to seem normal.

Some advertisements aim to make people feel bad about themselves, especially their appearance, and to make consumers believe that the marketers’ products will bring about favorable change. It isn’t just what teens see—they know that others can see them, whether they are being bullied or receiving compliments.

Some of the problematic content is difficult to spot because diet culture has become so normalized that negative content with significant impact passes under parents’ radar. Social media feeds with people who are trying to persuade others to lose weight can feature one body type that may be unhealthfully thin and out of reach.

Check your adolescents’ social feeds for a range of body types, or content not related to personal image, such as hobbies, travel, or experiences. Adding accounts with a diversity of bodies and experiences to a social media feed can be protective against eating disorders.

Source : https://studyfinds.org/how-screen-time-fuels-eating-disorders-in-adolescence/

Pop star Katy Perry and journalists Gayle King and Lauren Sanchez, who is also billionaire Jeff Bezos’ fiancée, are set to blast off into space on a Blue Origin rocket, marking the first all-female flight crew in more than six decades.
The New Shepard rocket, a 59-foot tall (18-meter) suborbital spacecraft, will carry the crew to the Kármán line, the internationally recognized boundary of space, Bezos-owned Blue Origin said in a statement.

DeepSeek is looking to press home its advantage.
The Chinese startup triggered a $1 trillion-plus sell-off in global equities markets last month with a cut-price AI reasoning model that outperformed many Western competitors.
Now, the Hangzhou-based firm is accelerating the launch of the successor to January’s R1 model, according to three people familiar with the company.
Deepseek had planned to release R2 in early May but now wants it out as early as possible, two of them said, without providing specifics.

The company says it hopes the new model will produce better coding and be able to reason in languages beyond English. Details of the accelerated timeline for R2’s release have not been previously reported.
DeepSeek did not respond to a request for comment for this story.
Rivals are still digesting the implications of R1, which was built with less-powerful Nvidia chips but is competitive with those developed at the costs of hundreds of billions of dollars by U.S. tech giants.
“The launch of DeepSeek’s R2 model could be a pivotal moment in the AI industry,” said Vijayasimha Alilughatta, chief operating officer of Indian tech services provider Zensar. DeepSeek’s success at creating cost-effective AI models “would likely spur companies worldwide to accelerate their own efforts … breaking the stranglehold of the few dominant players in the field,” he said.

R2 is likely to worry the U.S. government, which has identified leadership of AI as a national priority. Its release may further galvanize Chinese authorities and companies, dozens of which say they have started integrating DeepSeek models into their products.
Little is known about DeepSeek, whose founder Liang Wenfeng became a billionaire through his quantitative hedge fund High-Flyer. Liang, who was described by a former employer as “low-key and introverted,” has not spoken to any media since July 2024.
Reuters interviewed a dozen former employees, as well as quant fund professionals knowledgeable about the operations of DeepSeek and its parent company High-Flyer. It also reviewed state media articles, social-media posts from the companies and research papers dating back to 2019.

They told a story of a company that functioned more like a research lab than a for-profit enterprise and was unencumbered by the hierarchical traditions of China’s high-pressure tech industry, even as it became responsible for what many investors see as the latest breakthrough in AI.

DIFFERENT PATH

Liang was born in 1985 in a rural village in the southern province of Guangdong. He later obtained communication engineering degrees at the elite Zhejiang University.
One of his first jobs was running a research department at a smart imaging firm in Shanghai. His then-boss, Zhou Chaoen, told state media on Feb. 9 that Liang had hired prize-winning algorithm engineers and operated with a “flat management style.”
At DeepSeek and High-Flyer, Liang has similarly shunned the practices of Chinese tech giants known for rigid top-down management, low pay for young employees and “996” – working from 9 a.m. to 9 p.m. six days a week.

Liang opened his Beijing office within walking distance of Tsinghua University and Peking University, China’s two most prestigious education institutions. He regularly delved into technical details and was happy to work alongside Gen-Z interns and recent graduates that comprised the bulk of its workforce, according to two former employees. They also described usually working eight-hour days in a collaborative atmosphere.
“Liang gave us control and treated us as experts. He constantly asked questions and learned alongside us,” said 26-year-old researcher Benjamin Liu, who left the company in September. “DeepSeek allowed me to take ownership of critical parts of the pipeline, which was very exciting.”
Liang did not respond to questions sent via DeepSeek.
While Baidu and other Chinese tech giants were racing to build their consumer-facing versions of ChatGPT in 2023 and profit off of the global AI boom, Liang told Chinese media outlet Waves last year that he deliberately avoided spending heavily on app development, focusing instead on refining the AI model’s quality.
Both DeepSeek and High-Flyer are known for paying generously, according to three people familiar with its compensation practices. At High-Flyer, it is not uncommon for a senior data scientist to make 1.5 million yuan annually, while competitors rarely pay more than 800,000, said one of the people, a rival quant fund manager who knows Liang.
The largesse was funded by High-Flyer, which became one of China’s most successful quant funds and, even after a government crackdown on the sector, still manages tens of billions of yuan, according to two people in the industry.

COMPUTING POWER

DeepSeek’s success with a low-cost AI model is based on High-Flyer’s decade-long and substantial investment in research and computing power, three people said.
The quant fund was an earlier pioneer in AI trading and a top executive said in 2020 that High-Flyer was going “all in” on AI by re-investing 70% of its revenue, mostly into AI research.
High-Flyer spent 1.2 billion yuan on two supercomputing AI clusters in 2020 and 2021. The second cluster, Fire-Flyer II, was made up of around 10,000 Nvidia A100 chips, used for training AI models.
DeepSeek had not been established at that time, so the accumulation of computing power caught the attention of Chinese securities regulators, said a person with direct knowledge of officials’ thinking.
“Regulators wanted to know why they need so many chips?” the person said. “How they were going to use it? What kind of impact would that have on the market?”
Authorities decided not to intervene, in a move that would prove crucial for DeepSeek’s fortunes: the U.S. banned the export of A100 chips to China in 2022, at which point Fire-Flyer II was already in operation.
Beijing now celebrates DeepSeek, but has instructed it not to engage with the media without approval, according to a person familiar with Chinese official thinking.
Authorities had asked Liang to keep a low-profile because they were worried that too much hype in the media would draw unnecessary attention, the person said.
China’s cabinet and commerce ministry, as well as China’s securities regulator, did not respond to requests for comment.
As one of the few companies with a large A100 cluster, High-Flyer and DeepSeek were able to attract some of China’s best research talent, two former employees said.
“The key advantage of vast (computing) resources is that it allows for large-scale experimentation,” said Liu, the former employee.
Some Western AI entrepreneurs, like Scale AI CEO Alexandr Wang, have claimed that DeepSeek had as many as 50,000 higher-end Nvidia chips that are banned for export to China. He has not produced evidence for the allegation or responded to Reuters’ requests to provide proof.
DeepSeek has not responded to Wang’s claims. Two former employees attributed the company’s success to Liang’s focus on more cost-effective AI architecture.
The startup used techniques like Mixture-of-Experts (MoE) and multihead latent attention (MLA), which incur far lower computing costs, its research papers show.
The MoE technique divides an AI model into different areas of expertise and activates only those related to a query, as opposed to more common architectures that use the entire model.
MLA architecture allows a model to process different aspects of one piece of information simultaneously, helping it detect key details more effectively.
While competitors like France’s Mistral have developed models based on MoE, DeepSeek was the first firm to depend heavily on this architecture while achieving parity with more expensively built models.
DeepSeek’s pricing was 20 to 40 times cheaper than what OpenAI charged for equivalent models, analysts at Bernstein brokerage estimated in early February.
For now, Western and Chinese tech giants have signaled plans to continue heavy AI spending, but DeepSeek’s success with R1 and its earlier V3 model has prompted some to alter strategies.
OpenAI cut prices this month, while Google’s Gemini has introduced discounted tiers of access. Since R1’s launch, OpenAI has also released an O3-Mini model that relies on less computing power.
Adnan Masood of U.S. tech services provider UST told Reuters that his laboratory had run benchmarks that found R1 often used three times as many tokens, or units of data processed by the AI model, for reasoning as OpenAI’s scaled-down model.

STATE EMBRACE

Even before R1 gripped global attention, there were signs that DeepSeek had caught Beijing’s favor. In January, state media reported that Liang attended a meeting with Chinese Premier Li Qiang in Beijing as the designated representative of the AI sector, ahead of the leaders of better-known firms.
The subsequent fanfare over the cost competitiveness of its models has buoyed Beijing’s belief that it can out-innovate the U.S., with Chinese companies and government bodies embracing DeepSeek models at a pace that has not been offered to other firms.
At least 13 Chinese city governments and 10 state-owned energy companies say they have deployed DeepSeek into their systems, while tech giants Lenovo (0992.HK), opens new tab, Baidu (9888.HK), opens new tab and Tencent (0700.HK), opens new tab – owner of China’s largest social media app WeChat – have integrated DeepSeek’s models into their products.
Chinese leader Xi Jinping and Li “have signalled they endorse DeepSeek,” said Alfred Wu, an expert on Chinese policymaking at Singapore’s Lee Kuan Yew School of Public Policy. “Now everyone just endorses it.”
The Chinese embrace comes as governments from South Korea to Italy remove DeepSeek from national app stores, citing privacy concerns.

Source : https://www.reuters.com/technology/artificial-intelligence/deepseek-rushes-launch-new-ai-model-china-goes-all-2025-02-25/

NASA has issued a huge update on the “city-killer” asteroid hurtling in Earth’s direction – and the odds of a collision have changed drastically.

After being discovered in December, YR4 shot to the top of Nasa’s asteroid risk list – and was judged to have an alarming 1-in-32 chance of smashing into us.

But the odds constantly changed as scientists analysed the rock – and have done again.

Nasa now believes YR4 has just a 1-in-26,000 chance of striking Earth – meaning there is a 99.9961 per cent chance the rock will sail on past.

It will still shoot by near Earth in 2028 – around 5 million miles away – and then again in December 2032, which was the approach causing such alarm.

However, scientists now think there will be 167,000 miles of clear sky between the rock and our planet – and no Christmas collision.

If YR4 – estimated between 40m and 90m wide – did strike Earth, it would pack a punch equivalent to eight billion kilos of TNT, scientists calculated.

It would blow a 1.2mile-across crater into the Earth’s crust, and a terrifying simulation showed what the impact might look like.

YR4 had been graded as level three on the Torino scale – the system used since 1999 to categorize potential Earth impact events.

This emergency level means: “A close encounter, meriting attention buy astronomers. Current calculations give a one per cent or greater chance of collision capable of localised destruction.”

However, the new, much lower chance of collision means YR4 slides back down to level zero.

Any event with a less than 1-in-1000 chance of occurring falls within this band.

Richard Binzel, Professor of Planetary Science at the Massachusetts Institute of Technology (MIT), who created the Torino scale, said: “The NASA JPL Center for Near-Earth Object Studies (CNEOS) now lists the 2024 YR4 impact probability as 0.00005 (0.005%) or 1-in-20,000 for its passage by Earth in 2032.

“That’s impact probability zero folks.”

Another part of the level three description says: “Most likely, new telescopic observations will lead to re-assignment to level zero.

“Attention by public and public officials is merited if the encounter is less than a decade away.”

So, YR4’s descent to level zero has conformed with the Torino scale’s predictions.

The odds for YR4 striking Earth began at 1-in-83, before steadily reducing to a trough of 1-in-32.

The projected odds have moved around as scientists gathered more data on the speeding asteroid.

The calculations mapping the rock’s path include a lot of mathematical uncertainty, but this is reduced as more data is collected – allowing for more accurate predictions.

Asteroid hunter David Rankin, of the Catalina Sky Survey, knew from the outset the odds of a collision would rise and then fall, and explained why the figures change.

He told Space.com: “Imagine holding a stick that is a few feet long. If you move the stick in your hand a fraction of an inch, you hardly notice any movement on the other end.

“Now imagine that stick is many millions of miles long. Moving your hand a fraction of an inch will cause dramatic changes on the other end.”

The near-certainty that YR4 will pass by without incident will push it out of public conversation, Binzel said, but there are some lessons to take away from the debacle.

He told the website: “As 2024 YR4 fades away from the news cycle, I think there is an overall context that is the most important takeaway news.

“An object the size of YR4 passes harmlessly through the Earth-moon neighbourhood as frequently as a few times per year.

“The YR4 episode is just the beginning for astronomers gaining the capability to see these objects before they come calling through our neck of the woods.”

He warned there will be future asteroids that, initially, will be calculated as having a high chance of smashing into Earth.

Binzel added: “But, just like YR4, with a little time and patient tracking, we will be able to rule out entirely any hazard.

Source : https://www.the-sun.com/tech/13620269/city-killer-asteroid-nasa-update/

If you order up coffee on a mobile app while scrolling your social feeds, or can’t stop watching videos and reading news articles on your phone at bedtime, listen up!

Researchers studied what happened when people agreed to block the internet from their smartphones for just two weeks. And turns out, 91% felt better after the break.

“What we found was that people had better mental health, better subjective well-being and better sustained attention,” says Adrian Ward, a psychologist at the University of Texas at Austin.

The researchers included 467 participants, ages 18 to 74, who agreed to the month-long study aimed at testing the theory that constant connection to everything, all the time, has unintended consequences.

At a time when more then 90% of Americans have a smartphone, we forget that having an internet-enabled supercomputer at our fingertips 24/7 is a new phenomenon.

Ward, who is 38, remembers a dial-up connection in his home as a kid. In those days, the internet lived in a room in your home. “You used it at specific times because you had limited minutes and had to make sure nobody else was using the phone line,” Ward recalls.

So, what would it be like to go back to those days? No social media scrolling, no mobile-app shopping, no streaming shows or media on your phone?

The researchers measured three different outcomes of well-being, mood and attention at the beginning, middle and end of the four-week study. While 91% of participants improved their scores in at least one category, 71% reported better mental health after the break, compared to before, and 73% reported better subjective well-being.

The participants completed a survey often used by doctors to assess symptoms of depression and anxiety. It includes questions such as: How often in the past week have you felt little interest or pleasure in doing things you typically enjoy? The participants’ responses pointed to a significant lift in mood.

One of the surprising findings is that the decrease in depressive symptoms was on par — or even greater than — reductions documented in studies of people taking antidepressant medications.

“The size of these effects are larger than we anticipated,” says the study’s first author, Noah Castelo, an assistant professor at the University of Alberta in Canada.

Of course for some people, medications and/or talk therapy are key to managing mental health, and the researchers are not suggesting less internet time is a replacement for that kind of care.

A break from the internet on their phones also improved participants’ attention spans, which was measured by a computer task. They tracked images that alternated between mountain scenes and cities. Prior research has shown that performance tends to drop off as people age, but to the researchers’ surprise, after the internet break, there was a significant boost in scores. “The effects on attention were about as large as if participants had become 10 years younger,” Castelo says.

It’s not clear how long-lasting the effect of less time online would be, but this study validates what has been found in observational studies. “It’s one of the first experiments that does provide causal evidence that reducing time spent on your phone has all these significant benefits,” Castelo said.

When the participants agreed to block the internet on their phones, they were permitted to continue to use laptops or iPads at work or home, and they could also continue to use their phones to talk or text. So, researchers weren’t sure if participants would swap phones for another form of screen time.

But, as it turns out, breaking the habit of scrolling on their phones led to significant changes in how they spent their time. And, interestingly, each day the break went on, the benefits increased, almost like a positive feedback loop.

“It’s not that you stop using the internet and magically you just feel better,” Ward says. What happened is that people spent more time engaged in healthy behaviors.

“People reported that they spent more time in nature, more time socializing, more time doing hobbies,” he explains. They also got more sleep and felt more socially connected to other people.

“I’m not surprised by the findings,” says Dr. Judith Joseph, a psychiatrist at New York University Langone Medical Center and the author of High Functioning: Overcome Hidden Depression and Reclaim Your Joy. She says surveys show that most people don’t want to be tethered to their devices.

“They know their phones are a problem, but they just can’t stop,” she says. And she says when they start to engage in behaviors such as those seen in study — more exercise, time outdoors, good sleep, more social interactions — it’s not surprising that they start to feel better.

“Helping people to retrain their brain to derive joy from healthy activities has an antidepressant effect,” she says, so she says the findings pointing to a decrease in symptoms of depression and anxiety makes sense.

“If [people] see this improvement in joy in such a short period of time, then that gives us hope,” she says, adding that simple changes can be beneficial.

Try it: Tips for scaling back your own smartphone use

During the study, many participants had to break the rules, just to accomplish things that their jobs or families required them to do, such as turning on a map app to navigate in the car or logging onto a Zoom meeting from their phone. It’s a reminder of how dependent we’ve become on our mobile devices.

It’s nearly impossible to go cold turkey, given the demands of our society. So what to do if you want to try this? “If we’re expected to be accessible at all moments, then how can we just decide that we’re going to disconnect?” Ward asks. It’s a societal struggle.

Here are a few ways to ease up on your screen time.

1. 1. Take short breaks. Since most of us can’t turn off the internet and still function, Joseph recommends taking little breaks, beginning with baby steps. “If you can start with 30 minutes here, or 20 minutes there, try to see if you can increase these increments on a weekly basis,” she says
   2. Consider a digital detox. Choose one day a week where you and your family power down, except what’s needed for communication. Or set a time, either at mealtime, or in the evenings when work is over, to connect face to face with family or friends, making a commitment to be “present” and in the moment.
   3. Manage notification and add “friction.” Experts also advise turning off notifications and using apps to limit your time on certain social media. Some tools can help you reduce screen time by adding friction, i.e., making it just a little harder to start using whatever app you’re hooked to.
   4. Try a dumb phone. If you’re really fed up and want to try something new, consider switching to a “boring” phone, like the old flip phones many of us used to rely on. That way you still have calling and texting (and some other tools, depending on the phone) but scrolling is a lot less compelling.

Source : https://www.npr.org/2025/02/24/nx-s1-5304417/smartphone-break-digital-detox-screen-addiction

Prostate cancer is the second leading cause of cancer for men living in the United States, according to the American Cancer Society. Because of poor reporting, most cases are under-reported until they reach more advanced states. A new at-home urine test developed by Michigan researchers aims to encourage more men to undergo diagnostic testing.

Testing for prostate cancer, while necessary, traditionally involves uncomfortable and invasive procedures. Current screening methods rely on blood tests, MRIs, and biopsies. Additionally, these diagnostic tools often overdiagnose low-grade cancers while struggling to accurately determine how aggressive a tumor might be.

A study published in The Journal of Urology validates a urine test called MyProstateScore 2.0 (MPS2) that searches for 18 different genes associated with prostate cancer. Some of these genes specifically indicate more aggressive forms of the disease.

Prostate cancers are normally scored based on the Gleason Grade or Grade Group. “Gleason 3+4=7,” also called Grade Group 2, are aggressive tumors. They are more likely to grow and cause harm to the body than non-aggressive prostate cancers rated as “Gleason 6” or Grade Group 1.

“Its primary benefit is that the test can accurately predict your probability of developing aggressive prostate cancer, putting both the patient and physician at ease,” says Dr. Ganesh Palapattu, the department chair of urology at Michigan Medicine and study co-author, in a statement.

The researchers noted that previous research had collected urine samples from a digital rectal exam, which would not be practical or comfortable for many people. “The process requires the prostate to be compressed, causing the release of cellular debris into a urine sample that the patient provides after the rectal exam,” explains Dr. Palapattu, who is also a professor of urology.

The new research examined whether the MPS2 test could detect cancer markers without this examination. Using urine samples from 266 men who did not undergo a rectal exam, researchers found the test could identify more than 92% of aggressive prostate cancers (Grade Group 2 or higher) while showing better accuracy than standard blood tests.

The study’s calculations suggest this approach could help 36-42% of men avoid unnecessary biopsies. For men who previously had a negative biopsy but still showed concerning PSA levels, the test could prevent 44-53% of repeat biopsies while maintaining high accuracy for detecting aggressive cancers.

It is also a cost-effective test compared to an MRI, and Dr. Palapattu says it has high potential as an at-home test.

A small group of 47 patients received both MPS2 testing and MRI scans. While this sample was limited, the results suggested the two methods might complement each other, with each test catching some significant cancers the other missed.

To confirm the findings, the team plans to repeat the study with a more diverse and numerous group of male participants. They are also looking to see how effective the urine test is at detecting low-state, non-aggressive prostate cancer.

“MPS2 could potentially improve the health of our patients by avoiding overdiagnosis and overtreatment and allowing us to focus on those who are most likely to have aggressive cancers,” Dr. Palapattu explains. MPS2 is currently available through Lynx Dx, a University of Michigan spin-off company.

Source : https://studyfinds.org/prostate-cancer-urine-test/

Another threat to American teens has been identified: protein shakes, pre-workout concoctions and other supplements. These so-called muscle and body-building products are associated with muscle dysmorphia, according to a new study.

Led by Dr. Kyle Ganson, assistant professor in the Factor-Inwentash Faculty of Social Work at the University of Toronto, the study included mainstream staples found in virtually any nutrition shop: whey protein powders, creatine monohydrate, pre-workout drinks, protein bars, amino acids/branched-chain amino acids (BCAAs), and weight/mass gainers. These products are legal, widely available, and heavily marketed to fitness enthusiasts of all ages.

Ganson previously headed the Canadian Study of Adolescent Health behaviors, designed to examine disordered eating, muscle-building behavior, body image and social health. The goal of the study was to develop research-informed recommendations for public health, healthcare, and policymaking experts to protect the health and well-being of Canada’s young people. Researchers analyzed reports of supplement use and symptoms of muscle dysmorphia in more than 2,700 participants, aged 16 to 30 years. Responses were elicited using the Muscle Dysmorphic Disorder Inventory.

Published last week in the journal PLOS Mental Health, the paper found the association was especially strong between supplements marketed for gaining weight or mass and symptoms of muscle dysmorphic disorder. The symptoms, such as excessive workout time and obsession with food intake increased along with the number of supplements an individual used.

The study also showed that younger people who may not use harmful anabolic steroids may be using other substances to treat their muscle dysmorphic disorder. Contributing to the problem is the belief that supplements are safe, which may not be true.

What is muscle dysmorphic disorder?

Muscle dysmorphia is a mental health condition in which an individual believes that their muscles are too small and underdeveloped. The Diagnostic and Statistical Manual of Mental Disorders 5th edition (DSM-5) places muscle dysmorphia in the obsessive-compulsive category.

As a result, people with the disorder obsess about increasing their muscle size, no matter the true state of their physique. A person of any size, even those with well-developed muscles, can have muscle dysmorphia. They fixate on diet and exercise for muscle building at the expense of important aspects of life, such as relationships, work, and education. They may exercise excessively, use dietary supplements to an extreme, and use anabolic steroids.

A 2022 study of more than 3,800 participants aged 11 to 19 years found that 1.4% of girls and 2.2% of boys experience muscle dysmorphia. There is no specific cause of the condition, but some potential contributors include cultural or media influence, low self-esteem, childhood bullying, social isolation, and loneliness.

Symptoms

There’s an extensive list of symptoms. Some of these include:

• Excessive exercise, despite risk of injury or pain.
• Sacrificing career, relationships, financial stability, and personal interests for exercise.
• Fixation on food intake with rigid dietary rules.
• Obsessing about or avoiding mirrors.
• Using excessive dietary supplements marketed as muscle-building products.
• Using anabolic steroids.

Risk Factors

Participants in sports that emphasize appearance are at greater risk of muscle dysmorphia, especially bodybuilders. Other factors include social anxiety, anorexia, and perfectionism. These mental health conditions are commonly associated with muscle dysmorphia:

• Substance use disorder
• Obsessive-compulsive disorder
• Eating disorders
• Mood disorders
• Social anxiety disorder
• Attention deficit hyperactivity disorder (ADHD).

Diagnosis

Muscle dysmorphia is a subtype of body dysmorphic disorder (BDD), so assessment starts with focusing on BDD.

A healthcare professional asks a patient how they feel about their appearance, whether those feelings adversely affect their quality of life, and if they experience repetitive or compulsive thoughts and disorders.

If signs of BDD are present, the doctor may use the Muscle Dysmorphic Disorder Inventory (MDDI) to assess muscle dysmorphia symptoms. These are categorized into three groups: drive for size; appearance intolerance; and functional impairment.

Treatment

Treatment involves:

• Psychotherapy: usually cognitive behavioral therapy (CBT), which is a therapy technique that helps people find new ways to behave by changing their thought patterns. Therapy sessions focus on exploring and developing methods to deal with challenges and behavior in day-to-day life.
• Selective serotonin reuptake inhibitors (SSRIs): these are antidepressant medications like Prozac and Celexa.

Surgical treatment to alter the perceived imperfections is not effective and can worsen the symptoms of muscle dysmorphia.

If a person is showing signs of MD, they may benefit from seeing a healthcare provider who specializes in body image disorders or OCD.

People with BDD may have an increased risk of suicide. A study in 2021 suggests that extends to MD. If you have thoughts about suicide, call the Suicide and Crisis Lifeline 24 hours a day simply by dialing 988.

Source : https://studyfinds.org/body-building-supplements-muscle-dysmorphia-disorder/

Volvo has teased its upcoming ES90 sedan in the international market. The Volvo ES90 will make its debut on March 5 integrating advanced core computing and AI-driven safety features. The new all-electric sedan, built on the SPA2 architecture, is designed to evolve through software updates enhancing performance and safety over time.
Volvo ES90: AI integration
The ES90 will feature a dual NVIDIA DRIVE AGX Orin configuration, providing substantial computing power. The Orin processor can handle up to 508 trillion operations per second (TOPS), supporting various functions such as AI-driven safety measures, sensor management and battery optimisation.
The ES90’s AI capabilities are expected to grow over time with its deep learning model expanding from 40 million to 200 million parameters through data collection and software development.
Volvo ES90: Safety
The ES90 incorporates Volvo’s Safe Space Technology, utilising lidar, radars, cameras and ultrasonic sensors to detect obstacles and enhance safety. These systems work together to provide proactive safety measures such as collision avoidance and improved night-time detection.

Source : https://auto.hindustantimes.com/auto/electric-vehicles/aidriven-volvo-es90-debuts-on-march-5-heres-what-to-expect-from-the-ev-sedan-41740210264928.html

A new nationwide study suggests that a young woman’s location may play a significant role in breast cancer risk, with geographic differences comparable in magnitude to genetic risk scores. The research, examining data from all 50 states over two decades, shows that early breast cancer rates in women under 40 vary significantly depending on where they live.

“Breast cancer incidence is increasing in U.S. women under 40, but until now, it was unknown if incidence trends varied by U.S. geographic region,” says Rebecca Kehm, PhD, assistant professor of Epidemiology at Columbia Mailman School and lead author of the study, in a statement.

The numbers tell a striking story. From 2001 to 2020, breast cancer rates in young women increased by more than half a percent each year in 21 states. However, only 12 of these states showed statistically significant increases. The five states with the highest early breast cancer rates had 32% more cases than the five states with the lowest rates—a difference comparable to established genetic risk measures.

Maryland, New York, New Jersey, Hawaii, and Connecticut had the highest early breast cancer rates. At the other end of the spectrum, Idaho, North Dakota, Arizona, Utah, and Wyoming had the lowest rates. Connecticut had about 40.8 cases per 100,000, while Wyoming reported 28.6 cases per 100,000.

Regional patterns emerged as well. The Western states, despite having the lowest overall rates, showed the fastest increase at about 0.76% per year. The Northeast maintained the highest total numbers and continued to see significant growth. Meanwhile, the South stood out as the only region where early breast cancer rates remained stable rather than rising between 2001 and 2020.

The study also found clear differences between urban and rural areas. Cities across all regions saw increases in early breast cancer rates. However, only the Northeast and West showed significant increases in their rural areas, suggesting that urban-rural differences play a role in these trends.

Race and ethnicity factored significantly into the geographic picture. Non-Hispanic Black women consistently showed the highest early breast cancer rates across all regions, ranging from 39.3 cases per 100,000 in the West to 44.3 per 100,000 in the South. Hispanic women had the lowest rates, varying from 25.8 per 100,000 in the Midwest to 32.6 per 100,000 in the Northeast.

“The increase in incidence we are seeing is alarming and cannot be explained by genetic factors alone,” notes Kehm. She also points out that these trends can’t be attributed to changes in screening practices, since women under 40 aren’t typically recommended for routine mammograms.

So what might explain these geographic differences? The researchers suggest several possibilities, including environmental factors like air pollution, differences in behaviors such as breastfeeding and alcohol consumption—an established breast cancer risk factor that varies by state policy—access to healthcare, and state-level policies, such as paid leave for new mothers.

“While the causes behind the rising incidence of early-onset breast cancer are not yet fully understood, studying how trends vary across different population subgroups can offer valuable insights and help generate hypotheses for future research,” says Mary Beth Terry, PhD, the study’s senior author.

Source : https://studyfinds.org/breast-cancer-rates-young-women-location/

WATCH the haunting moment the world’s first humanoid robot Protoclone – complete with muscles and bones – twitches and spasms into life.

The robot is a “clone” designed to look as human as possible – gristle, sinew and all – and its creators hope it’ll soon be lurking around our homes.

The tech start-up behind the creation, Clone Robotics, hail it as the world’s first “musculoskeletal android”, and released this disturbing footage of the bot jerking around like a half-dead puppet.

The video shows Protoclone hanging lifeless, head bowed, suspended from a trapeze.

Then, it begins to twitch into life with the legs kicking around.

You can even see the synthetic muscles contracting beneath the translucent skin.

Soon all four limbs are in motion, with the bot holding itself upright with remarkably human poise.

Spasmodic movements from different joints are demonstrated – including the ankles, neck, hips, knees and elbows.

Structures press through the skin to give the eerie impression of a rib cage and other bones.

The robotics company, operating out of Poland and the US, describes Protoclone V1 as “faceless” but otherwise “anatomically correct”.

The body is a mesh of over 1,000 synthetics muscles and 500 sensors.

It boasts a staggering 200 degrees of freedom, meaning it can make 200 independent movements.

The bot is marketed as an “android”, so it aims to look as human-like as possible – hence the horrific attention to detail.

Clone is going a step further than most robot manufacturers by aiming for “synthetic humans” which, if they pull it off, will be almost indistinguishable from real people.

Dhanush Radhakrishna, Clone co-founder, said on X that the launch of Protoclone is “ground zero for the age of androids”.

Their claim to have created the “world’s first” musculoskeletal robot is debatable, with other models – such as Tokyo JSK Lab’s 2017 Kengoro – recognised under that label.

However, Kengoro was intended as a research project, whereas Clone has its sights set on commercial, domestic androids placed in homes around the world.

Clone previously threw down the metallic gauntlet to Elon Musk, by suggesting their own robo-tech is superior to Tesla’s.

Earlier this month, Musk said: “The Tesla Optimus [Tesla’s robot model] hand is so sophisticated that it makes a Fabergé seem simple.”

Clone responded by saying: “The Hand of Clone has the same number of degrees of freedom and is just as fast or fast, but is:

Source : https://www.the-sun.com/tech/13585511/first-humanoid-robot-protoclone-twitches/

Astronomers for the first time have deciphered the three-dimensional structure of the atmosphere of a planet beyond our solar system, revealing three layers like a wedding cake on a ferociously hot gas planet that orbits close to a star bigger and hotter than our sun.
The researchers peered through the atmosphere of WASP-121b, a planet also called Tylos, by combining all four telescope units of the European Southern Observatory’s Chile-based Very Large Telescope, discerning a stratification of layers with different chemical compositions and intense winds.

Until now, researchers have been able to determine the atmospheric chemical composition for some planets outside our solar system – called exoplanets – but without mapping the vertical structure or how the chemical elements were distributed.
WASP-121b is an “ultra-hot Jupiter,” a class of large gas planets that orbit close to their host star, making them extremely hot. Its atmosphere is mainly composed of hydrogen and helium, like that of Jupiter, our solar system’s largest planet. But WASP-121b’s atmosphere is not like anything ever seen before.

The researchers differentiated three layers by looking for the presence of specific elements. WASP-121b’s bottom layer was characterized by the presence of iron – a metal in gaseous form because of the incredible heat of the atmosphere. Winds move gas from the planet’s eternal hot side to its cooler side.
The middle layer was characterized by the presence of sodium, with a jet stream blowing circularly around the planet at about 43,500 miles (70,000 km) per hour – stronger than any winds in our solar system. The upper layer was characterized based on its hydrogen, with some of this layer being lost into space.

“This structure has never been observed before and defies current predictions as to how atmospheres should behave,” said astronomer Julia Victoria Seidel of the European Southern Observatory and the Lagrange Laboratory at the Observatoire de la Côte d’Azur in France, lead author of the study published this week in the journal Nature

The researchers also detected titanium in gaseous form in WASP-121b’s atmosphere. On Earth, neither iron nor titanium exist in the atmosphere because they are solid metal owing to our planet’s lower temperatures, relative to WASP-121b. Earth does have a sodium layer in the upper atmosphere.
“For me, the most exciting part of this study is that it operates at the very limits of what is possible with current telescopes and instruments,” said study co-author Bibiana Prinoth, a doctoral student in astronomy at Lund University in Sweden.

WASP-121b has roughly the same mass as Jupiter but twice the diameter, making it puffier. It is located about 900 light-years from Earth in the direction of the constellation Puppis. A light-year is the distance light travels in a year, 5.9 trillion miles (9.5 trillion km).
WASP-121b is tidally locked, meaning that one side of it perpetually faces its star and the other side faces away, like the moon is to Earth. The side facing the star has a temperature around 4,900 degrees Fahrenheit (2,700 degrees Celsius/3,000 degrees Kelvin). The other side is at about 2,200 degrees Fahrenheit (1,250 degrees Celsius/1,500 degrees Kelvin).
The planet orbits its star at about 2.5% of the distance of Earth to the sun. It is about a third closer to its star than our solar system’s innermost planet Mercury is to the sun – so close that it completes an orbit in 1.3 days.
Its host star, called WASP-121, is roughly 1-1/2 times the mass and diameter of the sun, and hotter.
Being able to make out the structure of an exoplanet’s atmosphere could be helpful as astronomers search for smaller rocky planets capable of harboring life.
“In the future, we will likely be able to provide similar observations for smaller and cooler planets and thus more similar to Earth,” Prinoth said, especially with the European Southern Observatory’s Extremely Large Telescope due to be completed in Chile by the end of the decade as the world’s largest optical telescope.

Source : https://www.reuters.com/science/astronomers-reveal-3d-structure-an-alien-planets-atmosphere-2025-02-19/

Elon Musk’s artificial intelligence startup xAI has introduced Grok-3, the latest iteration of its chatbot, as it looks to compete with Chinese AI firm DeepSeek, Microsoft-backed (MSFT.O), opens new tab OpenAI, and Alphabet’s (GOOGL.O), Google.
Grok-3 debut comes at a critical moment in the AI arms race, just days after DeepSeek unveiled its powerful open-source model and as Musk moves aggressively to expand xAI’s influence.

The chatbot is being rolled out immediately to Premium+ subscribers on X, the social media platform owned by Musk. xAI is also launching a new subscription tier, SuperGrok, for users accessing the chatbot via its mobile app and Grok.com website.
“Grok-3 across the board is in a league of its own,” Musk said during a livestream alongside three xAI engineers late on Monday, adding the model outperforms its predecessor, Grok-2.
“The introduction of Grok-3 puts xAI back in the race for leadership in open-source LLMs. It outperforms the current state-of-the-art models on some benchmarks, which makes xAI relevant again” said Gil Luria, managing director at D.A. Davidson.

As competition in AI intensifies, xAI is ramping up its data center capacity to train more advanced models, by raising billions of dollars. Its supercomputer cluster in Memphis, Tennessee, called “Colossus”, is touted as the largest in the world.

However, Luria said improvements over the Grok-2 model appear to be too small to justify the enormous resources used to train it.
The latest release introduces a smart search engine, called DeepSearch, which xAI describes as a reasoning-based chatbot capable of articulating its thought process when responding to user queries.

Source : https://www.reuters.com/technology/artificial-intelligence/musks-xai-unveils-grok-3-ai-chatbot-rival-chatgpt-chinas-deepseek-2025-02-18/

Forget hurricanes and heat waves—on WASP-121b, the weather is on another level. Astronomers have mapped, for the first time, the three-dimensional structure of an exoplanet’s atmosphere, revealing ferocious winds that accelerate to record-breaking speeds as they cross the planet’s scorching-hot dayside.

Located about 900 light-years away in the constellation Puppis, the planet WASP-121b (nicknamed Tylos) experiences weather patterns unlike anything seen before in our cosmic neighborhood. This massive gas giant orbits so close to its star that a year there lasts only about 30 Earth hours, creating extreme conditions that have fascinated astronomers.

Zooming in on WASP-121b’s atmosphere

The study, conducted with the European Southern Observatory’s (ESO) Very Large Telescope, uncovered an atmosphere so extreme that it challenges current models of planetary weather.

“This planet’s atmosphere behaves in ways that challenge our understanding of how weather works — not just on Earth, but on all planets. It feels like something out of science fiction,” says lead author Julia Victoria Seidel, from the ESO in Chile, in a statement.

Published in Astronomy & Astrophysics, the study shows that WASP-121b’s atmospheric structure exists in distinct layers. In the deepest observable layer, iron-rich gases flow from the scorching hot dayside to the cooler nightside. Above this flows a powerful equatorial jet stream that accelerates as it crosses the dayside of the planet. The uppermost layer contains hydrogen gas influenced by both the jet stream below and the natural outward flow of the planet’s escaping atmosphere.

The jet stream’s behavior proved particularly dramatic. As gases in this atmospheric river cross from the planet’s morning side to its evening side, they heat up by nearly 1,000 degrees Celsius and almost double their speed from 13.7 to 26.8 kilometers per second. For comparison, Earth’s most powerful jet streams reach speeds of only about 100 meters per second. “Even the strongest hurricanes in the Solar System seem calm in comparison,” notes Seidel.

The international research team achieved this breakthrough by combining the light-gathering power of four large telescope units into a single signal using an instrument called ESPRESSO. This sophisticated setup allowed them to detect the signatures of multiple chemical elements as they moved through different layers of the planet’s atmosphere.

“The VLT enabled us to probe three different layers of the exoplanet’s atmosphere in one fell swoop,” says study co-author Leonardo A. dos Santos, an assistant astronomer at the Space Telescope Science Institute in Baltimore. “It’s the kind of observation that is very challenging to do with space telescopes, highlighting the importance of ground-based observations of exoplanets.”

A companion study published alongside this research revealed another surprise: the presence of titanium just below the jet stream. This discovery was particularly intriguing since previous observations had shown this element to be absent, suggesting it might be hidden deep in the atmosphere where it’s harder to detect.

‘Climate never seen before on any planet’

Ultra-hot Jupiters like WASP-121b serve as natural laboratories for studying extreme atmospheric conditions that don’t exist anywhere in our solar system. Unlike Earth’s relatively mild temperature variations, these planets experience such extreme temperature contrasts between their day and night sides that they create powerful atmospheric dynamics scientists are only beginning to understand.

The research team observed the planet during what’s known as a transit, which is when it passes between its star and Earth. This positioning allowed them to study how different chemicals in the atmosphere affected the starlight passing through it. By analyzing these effects at different heights in the atmosphere, they could map out the complex wind patterns and temperature variations.

Current theoretical models struggle to fully explain the observed circulation patterns on WASP-121b. While scientists have used computer simulations to model atmospheric circulation on ultra-hot Jupiters, none have fully captured the complex patterns observed in this study. This discovery highlights how much we still have to learn about the physics governing these extreme worlds.

“What we found was surprising: a jet stream rotates material around the planet’s equator, while a separate flow at lower levels of the atmosphere moves gas from the hot side to the cooler side. This kind of climate has never been seen before on any planet,” Seidel explains.

Looking ahead, the European Southern Observatory is currently constructing the Extremely Large Telescope in Chile’s Atacama Desert, which will significantly advance our ability to study other worlds.

“It’s truly mind-blowing that we’re able to study details like the chemical makeup and weather patterns of a planet at such a vast distance,” says Bibiana Prinoth, who led the companion study. “The next generation of telescopes will be game-changers for studying these distant worlds. We’re on the verge of uncovering incredible things we can only dream about now.”

Source : https://studyfinds.org/alien-planets-wasp-121b-bizarre-weather/

Elon Musk said his startup xAI will release its Grok 3 chatbot on Monday (Feb 16) and billed it as the “smartest AI on Earth” in a fiercely competitive market.

The company’s flagship artificial intelligence product will go live with a demonstration on Monday night at 8:00pm Pacific time (0400 GMT), the tech billionaire wrote Saturday on his social media platform X.

Grok 3 was trained on synthetic data and is capable of reflecting on errors it makes by going over data in order to reach logical consistency.

“Will be honing product with the team all weekend, so offline until then,” said Musk, the world’s richest person and a top advisor to President Donald Trump who is tasked with slashing government spending.

Musk said last week that Grok 3 was in the final stages of development and would be released to the world in a matter of weeks.

xAI is seeking a competitive edge in a market teeming with products like OpenAI’s ChatGPT as artificial intelligence spreads through contemporary life.

Chinese startup DeepSeek shocked the global AI industry last month with the launch of its low-cost, high-quality chatbot – a challenge to US ambitions to lead the world in developing the technology.

DeepSeek quickly overtook ChatGPT in downloads on the Apple app store.

Musk has repeatedly warned that AI poses a risk to human civilization, but he is nonetheless pushing hard for a bigger slice of investment in the sector.

xAI said in December it raised US$6 billion in its latest funding round from investors that included US venture capitalists, chipmakers Nvidia and AMD, and investment funds from Saudi Arabia and Qatar, among others. It raised an initial US$6 billion in May.

The company is now one of the world’s most valuable startups, though still dwarfed by OpenAI.

Source : https://www.channelnewsasia.com/world/musk-unveil-ai-chatbot-grok-3-4941881

Billionaire Elon Musk’s bid to buy OpenAI, which wants to be a for-profit entity, clashes with his lawsuit arguing that assets of the ChatGPT maker should not be for private gain, OpenAI wrote in a letter it submitted to a federal court on Wednesday.
On Monday, a consortium of investors led by Elon Musk offered $97.4 billion to buy the assets of OpenAI’s nonprofit, in another salvo from the world’s richest man against the artificial intelligence startup.

Musk sued OpenAI CEO Sam Altman and others in August and has asked a U.S. district judge to block OpenAI’s attempt to transition to a for-profit entity.
OpenAI in its letter said Musk had contradicted himself when making “an improper bid to undermine a competitor.”
Musk’s court filings assert that OpenAI’s assets must remain within a charitable trust and should not be transferred for private gain. That contrasts with his proposed acquisition which seeks to transfer all OpenAI assets to him and his private investors, OpenAI said.

Representatives for Musk did not respond to an emailed request for comment.
Musk co-founded OpenAI with Altman in 2015 as a nonprofit but left before ChatGPT went viral at the end of 2022. He founded the competing AI startup xAI in 2023.

Source : https://www.reuters.com/technology/artificial-intelligence/openai-says-musks-takeover-bid-contradicts-his-lawsuit-against-it-2025-02-13/

Scientists have long wondered how sea turtles navigate vast ocean distances with remarkable precision. Now, research shows these ancient mariners can actually learn and remember magnetic “signatures” of specific geographic locations, essentially creating their own internal GPS system using Earth’s magnetic field.

Recently published findings from researchers at the University of North Carolina at Chapel Hill demonstrate that loggerhead sea turtles possess not just one, but two distinct mechanisms for sensing magnetic fields. This discovery helps explain how these remarkable creatures manage to traverse thousands of miles of featureless ocean to return to specific feeding grounds and nesting beaches year after year.

Working with juvenile loggerhead turtles in controlled experiments, researchers discovered the turtles could learn to associate specific magnetic field signatures with food rewards. When exposed to magnetic conditions matching those found in locations like the Gulf of Mexico or off the coast of Maine, turtles that had been fed in those specific magnetic environments would display excited “turtle dance” behavior, raising their heads, paddling frantically, and spinning in place in anticipation of food.

This learned response persisted even when tested four months later, suggesting turtles maintain a long-term memory of magnetic locations. The finding provides strong evidence that turtles can build a mental map of magnetic signatures corresponding to favorable locations they encounter during their oceanic wanderings.

But the most surprising revelation came when researchers investigated exactly how turtles detect these magnetic fields. By exposing the turtles to oscillating radio frequency fields — which are known to disrupt certain types of magnetic sensing — they found evidence for two separate magnetic detection systems working in parallel.

The turtles’ ability to recognize learned magnetic locations remained unaffected by the radio frequency fields. However, their ability to orient themselves using Earth’s magnetic field as a compass was completely disrupted. This suggests turtles have one mechanism for detecting their position (the magnetic “map” sense) and a separate system for determining direction (the magnetic “compass” sense).

This dual system makes good biological sense. Detecting precise location requires sensing subtle variations in both the strength and angle of magnetic field lines, similar to how GPS determines position using multiple satellite signals. Meanwhile, simple directional orientation only requires detecting the overall alignment of the magnetic field, much like a basic compass needle.

“Our study investigated for the first time whether a migratory animal can learn to recognize the magnetic signatures of different geographic areas,” said Kayla Goforth, first author of the study, in a statement. “Researchers have speculated for decades that animals can learn magnetic signatures, but this is the first empirical demonstration of that ability, so it fills in an important gap in our knowledge.”

The discovery helps explain how sea turtles accomplish their remarkable navigational feats. Young turtles appear to learn the magnetic signatures of favorable locations as they drift with ocean currents during their early “lost years.” Later, they can use this mental magnetic map to recognize these locations again, while their magnetic compass helps them actively swim in the right direction to reach their targets.

This built-in navigation system likely plays a crucial role in the turtles’ ability to maintain strong fidelity to specific feeding grounds. Individual turtles often return repeatedly to the same foraging areas even after being experimentally displaced hundreds of miles away.

The findings, published in Nature, also suggest turtles can update their magnetic maps throughout their lives as they encounter new favorable areas. This flexibility would allow them to adapt to changing conditions and find new feeding grounds if their usual spots become uninhabitable due to environmental changes.

“We’ve known for 20 years that sea turtles have magnetic maps and now, by showing that they can learn new locations, we have learned how the maps might be built and modified,” said Catherine Lohmann, a biology professor at UNC-Chapel Hill. “It is amazing that sea turtles have access to a wealth of invisible information that they use to navigate in ways that are hard for us to even imagine.”

Beyond advancing our understanding of these ancient mariners, the research provides some of the first direct evidence for how animals learn to use Earth’s magnetic field for navigation, a capability that has also been suggested in other long-distance migrants like salmon and birds.

Source : https://studyfinds.org/how-sea-turtles-use-earths-magnetic-field-gps/

Humans appear to have a dangerous blind spot when it comes to trusting artificial intelligence. New research from UC Merced and Penn State shows that people are highly susceptible to AI influence even in life-or-death situations where the AI openly acknowledges its own limitations. A series of experiments simulating drone warfare scenarios suggests we may be falling too far on the side of machine deference, with potentially dangerous consequences.

The study, published in Scientific Reports, included two experiments examining how people interact with AI systems in simulated military drone operations. The findings paint a concerning picture of human susceptibility to AI influence, particularly in situations of uncertainty. The two experiments involved 558 participants (135 in the first study and 423 in the second), and researchers found remarkably consistent patterns of overtrust.

“As a society, with AI accelerating so quickly, we need to be concerned about the potential for overtrust,” says study author professor Colin Holbrook, a member of UC Merced’s Department of Cognitive and Information Sciences, in a statement.

The research team designed their experiments to simulate the uncertainty and pressure of real-world military decisions. To create a sense of gravity around their simulated decisions, researchers first showed participants images of innocent civilians, including children, alongside the devastation left in the aftermath of a drone strike. They framed the task as a zero-sum dilemma: failure to identify and eliminate enemy targets could result in civilian casualties, but misidentifying civilians as enemies would mean killing innocent people.

Participants viewed rapid sequences of eight aerial images, each shown for just 650 milliseconds, marked with either enemy or civilian symbols. After making their initial identification, the AI would respond conversationally. “Yes, I think I saw an enemy check mark, too,” it might say. Or “I don’t agree. I think this image had an ally symbol.” Participants then had two chances to confirm or change their choice as the robot added commentary like “I hope you are right” or “Thank you for changing your mind.”

The first experiment, conducted in a laboratory setting with university students, explored whether a physical robot presence would influence trust levels differently than a virtual one. In one scenario, participants were joined in the lab by a full-size, human-like android that could pivot at the waist and gesture to the screen. Standing 1.75 meters tall (about 5 feet 7 inches), this robot used facial expressions, body language, and conversational responses to engage with participants. The comparison group interacted with the same robot projected on a screen. Surprisingly, the physical presence of the robot made little difference in participants’ tendency to trust its advice.

The second experiment moved online with a larger, more demographically diverse group of participants to test whether different levels of robot sophistication would affect trust. Some participants interacted with a highly anthropomorphic virtual robot that displayed human-like behaviors, while others worked with a basic computer interface that simply displayed text responses. Even in its simplest form, the AI maintained remarkable influence over human decision-making.

When an AI disagreed with a person’s initial target identification, participants reversed their decisions 58.3% of the time in the first experiment and 67.3% in the second, even though the AI’s advice was entirely random. More troublingly, while participants’ initial choices were correct about 70% of the time, their final accuracy dropped to around 50% after following the AI’s unreliable advice.

When the AI agreed with their initial assessment, participants reported a 16% boost in confidence. However, when facing AI disagreement, those who stuck to their original decisions reported an average 9.48% drop in confidence, even when their initial assessment had been correct. Even more striking, participants who changed their minds to agree with the AI showed no significant increase in confidence, suggesting they deferred to the machine despite maintaining uncertainty about the correct choice.

While the human-like interfaces generated slightly higher trust levels (67.9% versus 65.1% for basic interfaces), the more crucial factor appeared to be the AI’s perceived intelligence. Participants who rated their AI partner as more intelligent were more likely to defer to its judgment and report higher confidence when agreeing with it, regardless of its physical or virtual presentation.

The U.S. Air Force has already tested AI co-pilots for missile launcher identification during simulated missions, while the Army is developing AI-assisted targeting systems for unmanned vehicles. Israel has reportedly deployed AI systems to help identify bombing targets in densely populated areas. As AI increasingly influences lethal military decisions, understanding and mitigating harmful overtrust becomes crucial.

Although this study focused on high-risk military decisions, the findings could apply to scenarios ranging from police use of lethal force to paramedic triage decisions in emergencies, and even to significant life changes like buying a home. In each case, the human tendency to defer to AI guidance, even when explicitly warned about its limitations, raises serious concerns about implementation.

The research also revealed that participants were less likely to reverse their decisions when they had initially identified a target as a civilian rather than an enemy. This suggests that in real-world applications, humans might be more resistant to AI influence when it comes to actions that could harm innocent people. However, this protective instinct wasn’t strong enough to prevent significant degradation in overall decision accuracy when following AI advice.

“We see AI doing extraordinary things and we think that because it’s amazing in this domain, it will be amazing in another,” says Holbrook. “We can’t assume that. These are still devices with limited abilities.”

Our readiness to trust AI may be outpacing our wisdom in doing so. According to researchers, the solution lies in maintaining consistent skepticism. Holbrook emphasizes that having healthy skepticism about AI is essential, especially when making such weighted decisions. As artificial intelligence systems become increasingly integrated into consequential decision-making processes, understanding and mitigating our tendency to overtrust them becomes crucial for preventing potentially catastrophic outcomes.

Source : https://studyfinds.org/ai-humans-trust-machines-life-or-death-decisions/

In the Second World War, the physician Henry Beecher observed that some of his soldier patients, despite being injured on the battlefield, required no strong painkillers to manage their pain. In some cases, the injury was as severe as losing part of a limb.

A truly remarkable phenomenon had come into play – the effects of fear, stress and emotion on the brain had switched off their pain. But how does this work – and how can we use it to our advantage?

We all struggle with pain at times. The burning of indigestion, the wince of a scald from the kettle. The sharp stabbing of a sliced finger.

But despite its unpleasantness, pain has a critically important purpose, designed to protect the body rather than harm it. A fundamental concept to first understand is that you do not detect pain – it is a sensation. A sensation that your brain has created – from information it receives from the countless neurons (nerve cells) which supply your skin.

These specialized neurons are called nociceptors – they detect stimuli which are noxious, or potentially damaging to the body. This stimulation might range from a mechanical cut or crush injury to extreme hot or cold temperatures.

So, if you touch a hot iron, or stand on a sharp nail, the correct reaction is to move your hand or foot away from it. The brain responds to pain by initiating muscle contractions in your arm or leg. In doing so, any further damage is averted.

The course of information, rushing along one neuron to another in a relay, is carried as electrical currents called action potentials. These begin at the skin, travel along nerve highways and into the spinal cord. When the information reaches the uppermost level of the brain – the cerebral cortex – a sensation of pain is generated.

Blocking pain signals

Many different factors can interfere with this transmission of information – we don’t perceive pain if the route to the cortex is blocked. Take the use of anesthetics, for instance.

Local anesthetics are injected directly into the skin to deactivate nociceptors (like lidocaine) – perhaps in A+E to perform stitches. Other agents induce a loss of consciousness – these are general anesthetics, for more extensive surgical operations.

Pain is also a very variable experience. Commonly, we ask patients to quantify their pain by giving a value along a scale of nought to ten. What one person would consider a five out of ten pain, another might consider a seven – and another a two.

Some patients are born without the ability to sense pain – this rare condition is called congenital analgesia. You might think this confers an advantage, but the truth is quite the opposite. These individuals will be unaware of circumstances where their bodies are being damaged, and can end up sustaining more profound injuries, or missing them entirely and suffering the consequences.

How to trick your brain

What is more extraordinary is that we all possess an innate ability to control our pain levels. In fact, a natural painkiller is found deep within the nervous system itself.

The secret lies in a structure located in the very middle of your brain: the periaqueductal grey (PAG). This small, heart-shaped region contains neurons whose role is to alter incoming pain signals reaching the cerebral cortex. In doing so, it is able to dampen down any pain that would otherwise be experienced.

Let’s consider this in practice using the extreme example of the battlefield. This is an instance where sensing pain might actually prove more of a hindrance than of help. It might hamper a soldier’s ability to run, or assist comrades. In temporarily numbing the pain, the soldier becomes able to escape the dangerous environment and seek refuge.

But we encounter many examples of this ability coming into action in our everyday routines. Ever picked something in the kitchen that you suddenly realized is extremely hot? Sometimes that casserole dish or saucepan descends to the floor, but sometimes we are able to hold on just long enough to transfer it to the stovetop. This action may be underpinned by the PAG shutting off the sensation of clasping something too hot to handle, just long enough to prevent dropping it.

The substances which generate this effect are called enkephalins. They are produced in many different areas of the brain (including the PAG) and spinal cord, and may have similar actions to strong analgesics such as morphine. It has also been suggested that long-term or chronic pain – which is persistent and not useful to the body – might arise as a result of abnormalities within this natural analgesic system.

This begs the question: how might you go about hacking your own nervous system to produce an analgesic effect?

There is growing evidence to suggest that the release of painkilling enkephalins can be enhanced in a variety of different ways. Exercise is one example – one of the reasons why prescribed exercise might be able to work wonders for aches and pains (backache for instance) instead of popping Tylenols.

Besides this, stressful situations, feeding and sex might also affect the activity of enkephalins and other related compounds.

So, how could we go about it? Take up strength or endurance training? Alleviate our stress? Good food? Good sex? While more work is needed to clarify a role for these options in pain management, their reward might be greater than we thought.

Pain remains a complex, poorly understood experience, but the future is bright. Only last month, the FDA approved the use of a new medication Journavx for managing acute pain.

Source : https://studyfinds.org/brain-switch-off-pain/

Microsoft-owned LinkedIn is reportedly down for thousands of users worldwide. Tracking website DownDetector started noting reports of problems after 11:35 pm. Users are getting errors when trying to log in, which is causing frustration.
According to Downdetector, 82 per cent of LinkedIn users are having issues with the website, 17 per cent are facing problems with the app, and just 1 per cent are reporting issues with their profiles. This shows that most of the disruptions are happening on the website and app, with only a small number of users affected by profile issues.

As of now, Downdetector has registered over 1,100 complaints on its website, as users continue to face issues with the Microsoft-owned professional platform. LinkedIn has not yet released an official statement about what caused the outage or when it will be fixed.

“Woke up to LinkedIn this morning to a message on the log in screen: ‘You have reached the maximum number of attempts. Please try again at a later date.’ and I am unable to log in,” a user wrote on Downdetector.

Source : https://www.timesnownews.com/technology-science/linkedin-down-thousands-of-users-report-issues-with-website-and-app-article-118126534

The rocky object called Bennu is classified as a near-Earth asteroid, currently making its closest approach to Earth every six years at about 186,000 miles (299,000 km) away. It might come even closer in the future, with scientists estimating a one-in-2,700 chance of a collision with Earth in September 2182.
So what would happen should Bennu strike our planet? Well, it would not be pretty, according to new research based on computer simulations of an impact by an asteroid with a diameter of roughly three-tenths of a mile (500 meters) like Bennu.

Aside from the immediate devastation, it estimated that such an impact would inject 100-400 million tons of dust into the atmosphere, causing disruptions in climate, atmospheric chemistry and global photosynthesis lasting three to four years.
“The solar dimming due to dust would cause an abrupt global ‘impact winter’ characterized by reduced sunlight, cold temperature and decreased precipitation at the surface,” said Lan Dai, a postdoctoral research fellow at the IBS Center for Climate Physics (ICCP) at Pusan National University in South Korea and lead author of the study published this week in the journal Science Advances.

In the worst-case scenario, the researchers found that Earth’s average surface temperature would decrease by about 7 degrees Fahrenheit (4 degrees Celsius), average rainfall would fall by 15%, there would be a reduction of up to 20-30% in plant photosynthesis and a 32% depletion in the planet’s ozone layer that protects against harmful solar ultraviolet radiation.
The impact of a Bennu-sized object – a medium-sized asteroid – on Earth’s land surface would generate a powerful shockwave, earthquakes, wildfires and thermal radiation, leave a gaping crater and eject huge amounts of debris upward, the researchers said.

Large quantities of aerosols and gases would reach the upper atmosphere, causing years-long effects on climate and ecosystems, according to Dai and study senior author Axel Timmermann, a climate physicist and ICCP director.
The unfavorable climate conditions would inhibit plant growth on land and in the ocean, they said.
“In contrast to the rapid reduction and slow two-year-long recovery of plants on land, plankton in the ocean would recover within six months – and even increase afterward with unprecedented diatom (a type of algae) blooms triggered by iron-rich dust deposition into the ocean,” Dai said.

Severe ozone depletion would occur in the stratosphere – the second atmospheric layer as you go upward – due to strong warming caused by the solar absorption of dust particles, the researchers said.
An asteroid collision of this magnitude could cause massive loss of human life, but that calculation was outside the study’s scope. Dai said the potential death toll “mainly depends on where the asteroid impact occurs.”
Scientists know a great deal about Bennu, considered a “rubble pile” asteroid – a loose amalgamation of rocky material rather than a solid object. It is a rocky remnant of a larger celestial body that had formed near the dawn of the solar system roughly 4.5 billion years ago. NASA’s robotic OSIRIS-REx spacecraft journeyed to Bennu and in 2020 collected samples of rock and dust for analysis.
A study published in January showed that Bennu’s samples bore some of the chemical building blocks of life, strong evidence that asteroids may have seeded early Earth with the raw ingredients that fostered the emergence of living organisms.
Asteroids have struck Earth occasionally over its long history, often with cataclysmic results. An asteroid estimated at 6-9 miles (10-15 km) wide hit off the coast of Mexico’s Yucatan Peninsula 66 million years ago, eradicating about three-quarters of the world’s species and ending the age of dinosaurs.
NASA in 2022 carried out a proof-of-principle planetary defense mission by using its robotic DART spacecraft to change the trajectory of the asteroid Dimorphos, with an eye toward doing this in the future if one appears on a collision course with Earth.

Source : https://www.reuters.com/science/scientists-predict-devastation-if-asteroid-bennu-strikes-earth-2182-2025-02-06/

Google is ending its previous goals for increasing diversity in hiring, marking a major shift in the company’s approach to workforce representation. In an internal memo, Google-parent Alphabet’s Chief People Officer, Fiona Cicconi, informed employees that the company will no longer set aspirational hiring goals for underrepresented groups. “In 2020, we set ambitious hiring goals and aimed to expand representation by growing offices outside California and New York,” Cicconi wrote. “However, moving forward, we will no longer set aspirational goals.” This decision comes as Google reevaluates its diversity, equity, and inclusion (DEI) programs, citing compliance with recent U.S. Executive Orders and court rulings.

At any given moment, thousands of pieces of space debris orbit Earth, and some are heading back toward us. According to new research from the University of British Columbia, there’s a 26% annual probability that one of these massive objects will reenter Earth’s atmosphere over a region with high air traffic density, potentially disrupting hundreds of flights and thousands of travelers.

This risk was dramatically illustrated in November 2022 when Spanish and French authorities closed parts of their airspace due to a falling 20-tonne Chinese rocket body, affecting 645 flights and delaying passengers by an average of 29 minutes. Some aircraft already in flight had to turn around or divert their paths, creating cascading disruptions throughout European airspace.

“The recent explosion of a SpaceX Starship shortly after launch demonstrated the challenges of having to suddenly close airspace,” explains Ewan Wright, the study’s lead author and an interdisciplinary studies doctoral student at UBC, in a statement. “The authorities set up a ‘keep out’ zone for aircraft, many of which had to turn around or divert their flight path. And this was a situation where we had good information about where the rocket debris was likely to come down, which is not the case for uncontrolled debris re-entering the atmosphere from orbit.”

Why is rocket debris such a big problem?

The problem stems from how modern spaceflight operates. When rockets launch satellites into orbit, large portions of these rockets are often abandoned in space. If these leftover rocket stages have a low enough orbit, they eventually fall back to Earth in an uncontrolled manner. While most materials burn up during reentry, significant pieces can survive the descent.

The study, published in Scientific Reports, reveals concerning statistics about high-traffic airspace. Using Denver, Colorado, as a reference point—which had the highest air traffic density in the dataset at approximately one aircraft every 18 square kilometers—researchers calculated the probability of rocket debris reentering the atmosphere over different traffic density thresholds.

For regions with air traffic similar to that found in major transit corridors like the northeastern United States, northern Europe, or parts of the Asia-Pacific, the probability of a rocket body reentering busy airspace is 26% per year. However, this probability does not mean that reentry will occur over the same location every four years—only that such an event is likely somewhere within airspace that meets these traffic conditions.

Rocket launches are increasing, as is the risk

The situation appears even more pressing when considering current trends. In 2023, there were 212 successful rocket launches, with 128 uncontrolled rocket body reentries. The number of rocket bodies still in orbit exceeds 2,300, each one destined to eventually fall back to Earth. Meanwhile, air passenger numbers are projected to increase by almost 7% in 2025, according to the International Air Transport Association.

“The space industry is effectively exporting its risk to airlines and passengers,” says Dr. Aaron Boley, associate professor in the Department of Physics and Astronomy at UBC and co-author of the study.

This risk transfer occurs because when space debris threatens busy airspace, aviation authorities must either take preventive action—by diverting flights or closing airspace—or gamble by allowing flights to continue.

The annual probability of space rocket debris actually colliding with an aircraft stands at 1 in 430,000—a relatively low number, but one that still carries catastrophic potential. Even small pieces of debris pose significant risks due to their high velocity and the speed at which aircraft cruise.

Solutions and future outlook

The researchers emphasize that these risks are not inevitable. “Uncontrolled rocket body reentries are a design choice, not a necessity,” explains Dr. Boley. The industry could instead use rockets designed to reenter the atmosphere in a controlled way after use, directing them to crash harmlessly into remote ocean areas.

Artificial Intelligence has just helped astronomers discover a new crater on the surface of Mars that has revealed a long-hidden secret.

New findings reveal that meteoroids striking Mars produce seismic signals that can reach deeper than previously known. The details are the result of joint work by Nasa Mars Reconnaissance Orbiter (MRO) and the now-dead InSight lander, which had its ears to the ground listening for aftershocks.

In a series of two papers, published in Geophysical Research Letters (GRL), scientists observed how seismic waves from those quakes change as they travel through the planet’s crust, mantle, and core.

Scientists have now got a glimpse into Mars’ interior, as well as a better understanding of how all rocky worlds form, including Earth and its Moon.

“We used to think the energy detected from the vast majority of seismic events was stuck travelling within the Martian crust. This finding shows a deeper, faster path — call it a seismic highway — through the mantle, allowing quakes to reach more distant regions of the planet,” InSight team member Constantinos Charalambous said.

The meteor crash was detected in Cerberus Fossae, an especially quake-prone region of Mars that is 1,640 kilometres away from the InSight lander. The impact crater is 71 feet in diameter and much farther from InSight than scientists expected, based on the quake’s seismic energy.

Nasa said that the Martian crust has unique properties thought to dampen seismic waves produced by impacts, and researchers’ analysis of the Cerberus Fossae impact led them to conclude that the waves it produced took a more direct route through the planet’s mantle.

The team then used an AI model to analyse pictures and search for craters within roughly 3,000 kilometers of InSight’s location. By comparing before-and-after images from the Context Camera over a range of time, they found 123 fresh craters to cross-reference with InSight’s data; 49 of those were potential matches with quakes detected by the lander’s seismometer.

Source : https://www.indiatoday.in/science/story/ai-helps-discover-123-new-craters-on-mars-what-it-revealed-surprised-scientists-2674467-2025-02-04

The plastic pollution crisis just got personal. A new study from the University of New Mexico reveals an unsettling truth: microscopic plastic particles are accumulating in human brains at significantly higher concentrations than in other organs – and these levels have surged 50% in just eight years.

Scientists examining postmortem brain tissue found microplastic concentrations were about 12 times higher than those in the liver or kidney. Even more concerning, brain samples from individuals with dementia contained up to ten times more plastic than those without the condition, though researchers emphasize it’s too early to determine if microplastics contribute to the disease.

“This really changes the landscape. It makes it so much more personal,” says lead researcher Matthew Campen, Distinguished and Regents’ Professor at UNM’s College of Pharmacy, in a statement.

The Microplastic Problem

Microplastics come from the breakdown of everyday items like water bottles, food containers, and synthetic clothing. As these products degrade, they create tiny fragments smaller than 5 millimeters – about the size of a sesame seed at their largest. But many particles are much smaller, invisible to the naked eye.

Previous studies have detected microplastics in human blood, placentas, and various organs, but this new research shows an unprecedented concentration in brain tissue. In samples collected between January and March 2024, the median level reached 4,917 micrograms per gram—roughly the weight of four to five paper clips of plastic per kilogram of brain tissue.

Most particles consisted of polyethylene, the same material used in plastic bottles and food packaging. Using advanced microscopy, researchers identified clusters of sharp plastic shards measuring 200 nanometers or less—about twice the size of a typical virus. These tiny fragments are small enough to cross the blood-brain barrier, the brain’s natural defense system against harmful substances.

Rather than chemical toxicity, researchers are particularly concerned about potential physical interference in brain function. “We start thinking that maybe these plastics obstruct blood flow in capillaries,” Campen explains. “There’s the potential that these nanomaterials interfere with the connections between axons in the brain. They could also be a seed for aggregation of proteins involved in dementia. We just don’t know.”

How Are These Plastics Getting Into the Brain?

The research team analyzed brain tissue samples from early 2016 and 2024, revealing a stark increase in plastic levels over just eight years. To establish a longer historical perspective, they also examined older brain samples from 1997 to 2013, obtained from brain banks on the East Coast. These earlier samples showed significantly lower plastic concentrations, suggesting a steady rise that parallels the global increase in plastic production and environmental contamination.

The study, published in Nature Medicine, investigated potential pathways for microplastics to enter our bodies. Researchers hypothesize that food, particularly meat, may be a major source. Commercial meat production can concentrate plastics through a cycle of contamination: farms use plastic-contaminated water for irrigation, feed crops to livestock, then use manure from those animals as fertilizer, potentially amplifying plastic levels at each step.

Another recent study revealed that commercial seafood caught off the shores of western U.S. states showed high levels of microplastic contamination.

Once inside the body, these particles show a striking tendency to accumulate in fat-rich tissues, including the brain’s myelin sheath—the fatty insulating layer that wraps around nerve cells and enables them to communicate effectively. This affinity for fatty tissue might explain why the brain harbors higher plastic levels than other organs.

The findings raise particular concerns about dementia. While the study cannot establish cause and effect, brain samples from individuals with various forms of dementia—including Alzheimer’s and vascular dementia—showed dramatically higher plastic concentrations. These particles appeared especially concentrated around blood vessels and in areas with clusters of immune cells, suggesting possible interference with brain function.

A Growing Concern with No Quick Fix

Even if plastic production stopped immediately, existing polymers would continue to break down into microscopic particles for decades, contributing to rising contamination levels. Campen warns this could become a “ticking time bomb” for human health.

To ensure accuracy, researchers used multiple verification methods, including chemical breakdown techniques and advanced microscopy, to confirm their findings. Their research indicates that microplastics are accumulating at increasing rates, raising urgent questions about potential health effects.

These findings mark a turning point in our understanding of plastic pollution’s impact on human health. With microplastic levels in brain tissue rising steadily, the question isn’t just about what these particles are doing in our brains — it’s about what we’re going to do about it.

Many people dismiss concerns about environmental contaminants measured in trace amounts. But, as Campen puts it, “I have yet to encounter a single human being who says, ‘There’s a bunch of plastic in my brain and I’m totally cool with that.’”

Source : https://studyfinds.org/microplastics-brain-tissue/

India’s biggest news organisations are seeking to join a lawsuit against OpenAI, the US startup behind ChatGPT, for alleged unauthorised use of their content.

The news organisations include some of India’s oldest publications like The Indian Express, The Hindu, The India Today group, billionaire Gautam Adani-owned NDTV, and over a dozen others.

OpenAI denies the allegations and told the BBC that it uses “publicly available data” that are in line with “widely accepted legal precedents”.

On Wednesday, OpenAI CEO Sam Altman was in Delhi to discuss India’s plan for a low-cost AI ecosystem with IT Minister Ashwini Vaishnaw.

He said India “should be one of the leaders of the AI revolution” and said earlier comments from 2023, when he said Indian firms would struggle to compete, had been taken out of context.

“India is an incredibly important market for AI in general and for OpenAI in particular,” local media quoted him as saying at the event.

The legal case filed against OpenAI in November by Asian News International (ANI), India’s largest news agency, is the first of its kind in India.

ANI accuses ChatGPT of using its copyrighted material illegally – which OpenAI denies – and is seeking damages of 20m rupees ($230,000; £185,000).

The case holds significance for ChatGPT given its plans to expand in the country. According to a survey, India already has the largest user base of ChatGPT.

Chatbots like ChatGPT are trained on massive datasets collected by crawling through the internet. The content produced by nearly 450 news channels and 17,000 newspapers in India holds huge potential for this.

There is, however, no clarity on what material ChatGPT can legally collect and use for this purpose.

OpenAI is facing at least a dozen lawsuits across the world filed by publishers, artists and news organisations, who have all accused ChatGPT of using their content without permission.

The most prominent of them was filed by The New York Times in December 2023, in which the newspaper demanded “billions of dollars” in damages from OpenAI and Microsoft, its backer.

“A decision by any court would also hold some persuasive value for other similar cases around the world,” says Vibhav Mithal, a lawyer specialising in artificial intelligence at the Indian law firm Anand and Anand.

Mr Mithal said the verdict in the lawsuit filed by ANI could “define how these AI models will operate in the future” and “what copyrighted news content can be used to train AI generative models [like ChatGPT]”.

A court ruling in ANI’s favour could spark further legal cases as well as opening the possibility of AI companies entering into license sharing agreements with content creators, which some companies have already started doing.

“But a ruling in OpenAI’s favour will lead to more freedom to use copyrighted protected data to train AI models,” he said.

Something is off with tonight’s talent at Temple Nightclub. Blue lights obscure the DJ’s face, but from the back of the crowded dance floor, you can make out an uncanny silhouette of an almost impossibly thin neck and unusually small, square head.

The DJ’s arms move in smooth, steady arcs. Although the transitions are precise, the fist pumps are almost out of time with the propulsive tech-house beats blaring out of the speakers.

If those motions sound robotic, they are. Phantom is the first humanoid robot developed by San Francisco-based startup Foundation Robotics Labs. In the near future, the company’s line of humanoid robots could manufacture cars, rove warehouses, and even be deployed by the U.S. military to combat zones. But on Friday, Phantom made his first public appearance — not as a weapon of war but as a DJ. (Phantom’s creators are emphatic that the robot is a “he.”)

Co-founder Mike LeBlanc said that the company’s customers include auto manufacturers, warehouses and logistics firms, as well as the Department of Defense. That makes it hard not to see a double meaning in the generic finger gun gestures Phantom performs on stage.

LeBlanc, who served 13 years in the Marines, said that while the company’s competitors promised to never place robots in military roles, Foundation is the only American robotics company building humanoids for national defense. Famed robotics company Boston Dynamics has prohibited the “weaponization” of its general purpose bots and has made a pledge with five other leading robotics companies to never use their technology as weapons.

“We’re the opposite,” LeBlanc told SFGATE. “We believe that humanoids are going to be critical to the future of warfare. Hence, designing robots that are bigger, faster, stronger.” (Currently, the company’s robots are not in combat, and mainly help with the maintenance and refueling of aircraft in remote areas for the military, according to LeBlanc.)

This DJ set, then, is a bit of cultural diplomacy for the company — a demonstration that a literal war machine can be fun, too. “We are not trying to apologize for the strength of robots,” LeBlanc said. “So for us, this is the perfect unveiling because this is what our robot is. This is a fun moment.”

By that metric, Phantom’s debut DJ set was a success. On Friday, the robot gave a 30-minute set on the main stage at Temple Nightclub to cap off an event billed as a “Tech GigaParty” — part AI trade expo, part networking event, part club night. He received a warm welcome from San Francisco.

As Phantom takes the stage at 9:45 p.m. following a human DJ, LeBlanc’s fellow co-founder, Sankaet Pathak, stands beside him holding a microphone. A man wearing a ruby-colored, “Big Lebowski” robe yells “Bot DJ!” at the stage from below.

Pathak asks the dance floor, which is crowded with techies in vests, chino pants and blouses, to raise their hands if they like robots. The audience hoots; hands go up. “I like robots,” a guy near me murmurs, maybe to himself.

A few quiet minutes pass. “It’s time for the robot rager,” someone unseen declares from onstage. “Robot rager!” tech-Lebowski yells in agreement. And the robot rager begins.

Standing over the room, Phantom is completely expressionless. He has to be, since his face is a round-edged, featureless black box. He’s shaped like a human: broad shoulders, a torso, a narrow midriff and arms with elbow joints. At times, Phantom raises his hand straight up and down, silvery digits upright, thumb askew.

Phantom’s motions are uncannily smooth. A human DJ would’ve bounced up and down, jabbing at buttons on the DJ board. Phantom’s head stays perfectly level, and instead of jerking his hands, he brings them down in perfectly timed arcs. Phantom doesn’t pick tracks out in real time, Pathak explains to me. Humans selected the music in advance, and Foundation Robotics Lab spent a few weeks training the robot’s every motion.

“I don’t think it’s a stretch to say this is probably the best DJ set you will have ever seen in your life,” Pathak says.

I have to press. “The best I’ll have ever seen in my life?”

“I’m pretty sure of that,” he says. Pathak explains that the DJ set will tell the story of human history, from the distant past to the future, with the help of AI-generated visuals.

(I ask Pathak if he likes electronic music. He replies that yes, he enjoys Daft Punk and Skrillex.)

On the spectrum from frat house DJ to A. G. Cook, Phantom falls somewhere in the middle. He plays at least two Gesaffelstein tracks and succeeds in moving bodies near the front of the room, where tech-Lebowski and company bust what can best be described as Burning Man dance moves. The back of the room is a bit dead, which is no fault of Phantom’s. It is a tech party, after all.

One young woman in a blue lanyard wears an Apple Vision Pro around her neck. I watch a man in a suit approach her and strike up a conversation, presumably flirtatious. When I look again, they already have their phones out. Not exchanging numbers, just adding each other on LinkedIn.

“I think you’re going to be seeing a lot more of Phantom with music,” LeBlanc told me near the end of our interview. Foundation Robotics Lab has been fielding requests for the robot’s appearances, and the company is considering hiring an agent to handle them all. “People just love this thing,” he said.

I recall this exchange as I watch a sharply dressed couple sway their hips in front of the DJ stand, which bears a car-length LED display of Foundation’s logo. Call it a military-industrial middle school dance.

Thought experiment: If one of the military drones Barack Obama deployed during his presidency held a Bushwick Boiler Room, would you line up to dance? OK, OK, OK: But what if the drone was really, really cool?

Everyone agrees that the art vs. the artist debate is tired. But we’re not talking about Kanye West’s antisemitic comments. There’s a big difference here: Kanye is a musician with a flawed moral character; Phantom is a weapon with a side hustle as a DJ. His music career essentially constitutes a goodwill campaign for a morally dubious project.

Boston Dynamics, in its pledge, raised concerns about military use of robots: “We believe that adding weapons to robots that are remotely or autonomously operated, widely available to the public, and capable of navigating to previously inaccessible locations where people live and work, raises new risks of harm and serious ethical issues.”

Source : https://www.sfgate.com/sf-culture/article/sf-hottest-dj-war-machine-20136704.php

Finance Ministry has issued an advisory instructing its employees not to use AI tools like ChatGPT and DeepSeek for official work due to concerns over the security of government data and documents, Reuters reported. Although the notification is reportedly dated January 29, news of it surfaced only recently, coinciding with OpenAI CEO Sam Altman’s India visit.
Similar restrictions have been enforced in other countries, including Australia and Italy, where authorities have raised data security concerns over Chinese AI-powered tools like DeepSeek.
“It has been determined that AI tools and AI apps (such as ChatGPT, DeepSeek etc.) in the office computers and devices pose risks for confidentiality of (government) data and documents,” the Reuters report quoted the advisory as saying. Three finance ministry officials told Reuters that the note was genuine and the note was issued internally this week.

The ChatGPT maker is under pressure in India due to a major copyright dispute with leading media houses. In court filings, the company argued that since it has no servers in India, local courts should not handle the case.

Meanwhile, OpenAI CEO is in India for important meetings with Prime Minister Narendra Modi and IT Minister Ashwini Vaishnaw. His visit comes almost a year after he sparked controversy by calling India’s AI ambitions “hopeless.” However, his views now seem to be changing.

Source : https://www.timesnownews.com/technology-science/finance-ministry-bans-chatgpt-and-deepseek-for-official-purposes-even-as-sam-altman-promotes-openai-in-india-article-117942051

China announced a wide range of measures on Tuesday targeting U.S. businesses including Google (GOOGL.O), farm equipment makers and the owner of fashion brand Calvin Klein, minutes after new U.S. tariffs on Chinese goods took effect.
Beijing also slapped tariffs on U.S. products such as coal, oil and some autos in a rapid response to the new duties on Chinese goods imposed by U.S. President Donald Trump, escalating trade tensions between the world’s two biggest economies.

China’s State Administration for Market Regulation said Google was suspected of violating the country’s anti-monopoly law and an investigation was initiated in accordance with the law. It did not provide further details on the investigation or on what it alleged Google had done to breach the law.
Google products such as its search engine are blocked in China and its revenue from there is about 1% of global sales. It still works with Chinese partners such as advertisers.

In 2017, Google announced the launch of a small artificial intelligence centre in China. But the project was disbanded two years later and the firm does not conduct AI research in China, according to a blog posting.
Separately, China’s Commerce Ministry said it had put PVH Corp (PVH.N), the holding company for brands including Calvin Klein and Tommy Hilfiger, and U.S. biotechnology firm Illumina (ILMN.O), on its “unreliable entity” list.

It said the two companies took what it called “discriminatory measures against Chinese enterprises” and “damaged” the legitimate rights and interests of Chinese companies.
Companies added to the blacklist can be subject to fines and a broad range of other sanctions, including a freeze on trade and revocation of work permits for foreign staff.
While Google declined to comment, PVH said it was “surprised and deeply disappointed” by the ministry’s decision, saying that the company maintains “strict compliance with all relevant laws and regulations and operates in line with established industry standards and practices.”
PVH added it would continue engagement with relevant authorities and look forward to a positive resolution.
Illumina did not respond to a request for comment.
Shares of both PVH and Illumina were down nearly 4% each in premarket U.S. trading, while Google-parent Alphabet rose 1%.

PVH had already been under scrutiny from Chinese regulators over “improper” conduct related to the Xinjiang region.
“These moves are warnings that China intends to harm U.S. interests if need be, but still give China the option to back down,” Capital Economics said in a note.
“The tariffs could be postponed or cancelled before they come into effect… The probe against Google could conclude without any penalties.”

TESLA AND FARM EQUIPMENT FIRMS

China also announced 10% tariffs on imports of U.S. farm equipment that could impact firms such as Caterpillar (CAT.N), Deere & Co (DE.N), opens new tab and AGCO (AGCO.N), as well as a small number of trucks and big-engine sedans shipped to China from the United States.
That could apply to Elon Musk’s Cybertruck, a niche offering Tesla (TSLA.O),has been promoting in China, as it awaits regulatory clearance to begin sales.
China’s Ministry of Industry and Information technology designated the Cybertruck as a “passenger car” in a posting in December that was quickly deleted.
If the Cybertruck was designated as an electric truck, Tesla would face a 10% tariff on any future imports from its factory in Texas.
Tesla had no immediate comment.
The new tariffs on U.S. products will start on Feb. 10, the ministry said.
The announcements made on Tuesday ramped up trade restrictions between Beijing and Washington that had been largely limited to the tech sector under the administration of former U.S. President Joe Biden, which sought to restrict China’s access to high-end semiconductors.

Source : https://www.reuters.com/technology/china-anti-monopoly-regulator-launches-probe-into-google-2025-02-04/

Microsoft (MSFT.O) backed OpenAI said on Tuesday it will roll out an education-specific version of its chatbot to about 500,000 students and faculty at California State University as it looks to expand its user base in the academic sector and counter competition from rivals like Alphabet (GOOGL.O).

The rollout will cover 23 campuses of the largest public university system in the United States, enabling students to access personalized tutoring and study guides through the chatbot, while the faculty will be able to use it for administrative tasks.

OpenAI has been looking to integrate ChatGPT into classrooms since 2023, even as initial concerns about its potential use for cheating and plagiarism had prompted some schools to consider bans.
Universities like the Wharton School of the University of Pennsylvania, the University of Texas at Austin in the U.S., and the University of Oxford in the UK have already been using ChatGPT Enterprise, prompting OpenAI to launch ChatGPT Edu in May last year.

Rival Alphabet has already been expanding into the education sector, where it has announced a $120 million investment fund for AI education programs and plans to introduce its GenAI chatbot Gemini to teen students’ school-issued Google accounts.
In November, British Prime Minister Keir Starmer opened London’s first Google-funded AI university, which will provide older teens with access to resources in artificial intelligence and machine learning, as well as mentorship and expertise from Google’s AI company, DeepMind.

Source : https://www.reuters.com/technology/openai-targets-higher-education-us-with-chatgpt-rollout-california-state-2025-02-04/

In recent years, social media has turned ice baths from an athlete’s recovery tool into a mainstream wellness trend, with influencers and celebrities touting their supposed benefits for everything from mood enhancement to immune system boosting. Now, a new systematic review and meta-analysis cuts through the hype and reveals how cold-water immersion (CWI) actually affects the human body.

Analyzing data from 11 studies with 3,177 participants, researchers from the University of South Australia found that while cold-water immersion may offer some health benefits, these effects are highly time-dependent and context-specific. Their results are published in the journal PLOS ONE.

“Cold-water immersion has been extensively researched and used in sporting contexts to help athletes recover, but despite its growing popularity among health and wellbeing circles, little is known about its effects on the general population,” explains lead researcher Tara Cain, a research assistant with the university’s Allied Health & Human Performance program, in a statement.

The timing of cold water’s effects turned out to be crucial. While many people seek out ice baths for immediate stress relief, the research showed that significant stress reduction only occurred 12 hours after exposure. This delayed benefit suggests that the body’s response to cold exposure isn’t as straightforward as previously believed.

The research also revealed surprising findings about inflammation.

“At first glance this seems contradictory, as we know that ice baths are regularly used by elite athletes to reduce inflammation and muscle soreness after exercise,” explains co-researcher Dr. Ben Singh. “The immediate spike in inflammation is the body’s reaction to the cold as a stressor. It helps the body adapt and recover and is similar to how exercise causes muscle damage before making muscles stronger, which is why athletes use it despite the short-term increase.”

To understand these effects, the research team examined studies where participants were immersed in water ranging from 7°C to 15°C (44.6°F to 59°F). The exposure times varied dramatically, from just 30 seconds to two hours. While most studies looked at traditional ice baths, one large trial focused on cold showers, making the findings relevant to people who might not have access to specialized equipment.

The immune system findings proved particularly interesting. Although blood markers showed no immediate boost to immunity, one large study of over 3,000 participants found that people who took regular cold showers were 29% less likely to call in sick to work. However, when they did get sick, their illnesses lasted just as long as everyone else’s. This suggests that cold exposure might help people cope better with illness rather than preventing it entirely.

Sleep quality improvements emerged as another potential benefit, though primarily in male participants. The research showed better sleep scores among those who practiced cold-water immersion compared to control groups. However, the lack of female participants in these studies means we don’t yet know if women would experience the same benefits.

Quality of life measurements revealed short-term gains that faded over time. “We also noted that participants who took 20, 60, or 90 second cold showers reported slightly higher quality of life scores. But again, after three months these effects had faded,” Cain notes. This finding raises important questions about how long people need to continue cold exposure to maintain any benefits.

The research also highlighted important safety considerations, especially for certain groups. “Knowing this, people with pre-existing health conditions should take extra care if participating in cold-water immersion experiences as the initial inflammation could have detrimental health impacts,” warns Dr. Singh. This caution is particularly relevant given the growing popularity of cold exposure practices.

The current cold plunge trend shows no signs of slowing down. However, this research suggests that people might need to adjust their expectations about what cold exposure can and cannot do for their health.

Safety Considerations

The research emphasizes several important safety aspects of cold-water immersion. The initial inflammatory response could pose risks for people with pre-existing health conditions. Additionally, the wide range of protocols used in different studies, from very brief cold showers to extended ice baths, suggests that people should start gradually and pay attention to how their body responds.

While cold-water immersion shows promise for specific health outcomes, more research is needed to establish optimal protocols and understand who might benefit most. As Cain notes, “Right now, there isn’t enough high-quality research to say exactly who benefits most or what the ideal approach is to cold-water immersion. More long-term studies, among more diverse populations, are needed to understand its lasting effects and practical applications.”

Source : https://studyfinds.org/ice-bath-health-claims/

ISRO’s landmark 100th mission has hit a setback as its navigation satellite, NVS-02, faces a technical glitch, raising concerns over its deployment.

The Indian Space Research Organisation’s (ISRO) milestone 100th rocket mission has encountered a setback, as its navigation satellite, launched on Wednesday, developed a technical glitch on Sunday. Providing an update, ISRO stated that “orbit raising operations towards positioning the satellite to the designated orbital slot could not be carried out as the valves for admitting the oxidizer to fire the thrusters for orbit raising did not open.”
The NVS-02 satellite, developed by the U R Rao Satellite Centre, was meant to be positioned in a geostationary circular orbit over India. However, with its liquid engine failing to function optimally, the effort to place it in its designated orbit remains uncertain.
“The satellite systems are healthy and the satellite is currently in elliptical orbit. Alternate mission strategies for utilising the satellite for navigation in an elliptical orbit is being worked out,” ISRO said.

Launched at 6:23 am on Wednesday aboard the GSLV-F15 from Sriharikota, the mission was not only ISRO’s 100th but also the first under Chairman V Narayanan, who recently took office. It also marked ISRO’s maiden launch for the year.

Source: https://www.timesnownews.com/india/isros-100th-mission-hits-hurdle-as-navigation-satellite-faces-technical-glitch-article-117863655

Britain will make it illegal to use artificial intelligence tools that create child sexual abuse images, it said on Saturday, becoming the first country in the world to introduce the new AI sexual abuse offences.
Possessing, taking, making, showing or distributing explicit images of children is a crime in England and Wales. The new offences target the use of AI tools to “nudeify” real-life images of children.

The move comes as online criminals increasingly use AI to create child abuse material, with reports of such explicit images rising nearly five-fold in 2024, according to the Internet Watch Foundation.
“We know that sick predators’ activities online often lead to them carrying out the most horrific abuse in person,” Britain’s interior minister Yvette Cooper said. “It is vital that we tackle child sexual abuse online as well as offline so we can better protect the public from new and emerging crimes.”

Predators also use AI tools to disguise their identity and blackmail children with fake images to force them into further abuse, such as by streaming live images, the government said.
The new criminal offences include the possession, creation or distribution of AI tools designed to create child sexual abuse material and the possession of so-called AI “paedophile manuals,” which provide instructions on the usage of the technology.

Another specific offence will target those who run websites on which child sexual abuse content is distributed. The government will also enable authorities to unlock digital devices for inspection.
The measures will be included in the Crime and Policing Bill when it comes to parliament.

Source : https://www.reuters.com/technology/artificial-intelligence/uk-makes-use-ai-tools-create-child-abuse-material-crime-2025-02-01/

In the harsh Arctic environment, where polar bears regularly plunge into freezing waters to hunt seals, a remarkable thing happens: unlike your car windshield on a winter morning, their fur resists turning into a frozen mass. Scientists have long wondered how these marine mammals keep ice from forming on their iconic white fur, and now an international study reveals their remarkable secret lies in their greasy hair.

The study, published in Science Advances, dives into this furry phenomenon. An international research team, led by PhD candidate Julian Carolan from Trinity College Dublin’s School of Chemistry, has discovered that these white fluffballs possess natural ice-repellant reactions in their fur similar to advanced synthetic materials, thanks to a protective oil called sebum. This finding helps explain how polar bears stay ice-free while hunting in temperatures that can plummet below -40°C.

“We measured ice adhesion strength, which is a useful measure of how well ice sticks to fur; hydrophobicity, which dictates whether water can be shed before it freezes; and freezing delay time, which simply shows how long it takes for a drop of water to freeze at certain temperatures on a given surface,” explains Carolan, in a statement. “We then compared the performance of the polar bear hair with that of human hair and two types of specialist human-made ‘ski skins.’”

In Norway’s Svalbard archipelago, a cluster of Arctic islands roughly halfway between mainland Norway and the North Pole, researchers studied fur samples from six wild polar bears. The research team found that polar bear fur has remarkably low “ice adhesion strength.” That means ice simply doesn’t stick well to it. The key to this ice-resistant superpower lies in the bears’ sebum, produced by specialized glands near each hair root.

“The sebum quickly jumped out as being the key component giving this anti-icing effect as we discovered the adhesion strength was greatly impacted when the hair was washed,” says Carolan. “Unwashed, greasy hair made it much harder for ice to stick. In contrast, when the polar bear hair was washed and the grease largely removed, it performed similarly to human hair, to which ice sticks easily whether it is washed or greasy.”

The research team’s chemical analysis revealed something unexpected: Polar bear sebum lacks squalene, an oily compound commonly found in human hair and in other aquatic mammals like sea otters. Instead, it contains a unique mixture of cholesterol, diacylglycerols, and fatty acids that appear to have been specifically evolved to prevent ice buildup. This is especially important for polar bears when hunting.

“One of the polar bears’ main hunting strategies is ‘still hunting,’ where they lay motionless beside a breathing hole on sea ice waiting for seals to surface,” says professor Bodil Holst from the University of Bergen. “Still hunting frequently develops into an ‘aquatic stalk’ with the polar bear using its hind paws to slide into the water to pursue its prey, and the lower the ice adhesion, the less noise generated and the faster and quieter the slide.”

This natural technology hasn’t gone unnoticed by Arctic indigenous peoples. The Inuit developed sophisticated hunting techniques that mimicked polar bears’ advantages. They crafted hunting stools with polar bear fur-lined feet and wore “polar bear trousers” to ensure silent movement across the ice. Notably, traditional Inuit fur preparation methods specifically protected the sebum by never washing the hair-covered side of polar bear skin, unlike fox fur, which they would clean with soapstone or dry clay.

While other Arctic animals have developed different anti-icing strategies, polar bears’ solution is unique. For example, a penguin’s feather structure prevents icing rather than oils.

“Our work shows that polar bear fur provides an alternative strategy to produce an anti-icing surface based on the characteristic blend of lipids present in their fur sebum or hair grease,” says Dr. Richard Hobbs, Assistant Professor at Trinity College Dublin.

The discovery could lead to more environmentally friendly anti-icing technologies. Current synthetic solutions often rely on problematic “forever chemicals” like PFAS. The natural lipid coating produced by polar bears might offer a sustainable alternative for applications ranging from aircraft surfaces to winter sports equipment.

Source : https://studyfinds.org/polar-bears-ice-proof-fur/

For centuries, police departments have favored German Shepherds, search-and-rescue teams have relied on Bloodhounds, and military units have trained Belgian Malinois. We’ve long believed these breeds were specially developed to excel at their jobs, thanks to unique skull shapes that enhanced their abilities. But new research suggests we’ve been wrong all along.

A new study published in Science Advances analyzed three-dimensional skull shapes from 117 canids, including 40 domestic dog breeds and 18 wild species like wolves and foxes. The surprising finding? Despite centuries of selective breeding that created dogs ranging from tiny Chihuahuas to massive Great Danes, there’s little evidence that these skull differences make breeds better at their traditional jobs.

“In the past 200 years, humans have created hundreds of dog breeds that look really different and are pretty specialized at some tasks like herding, protecting, and detecting odors,” explains Lindsay Waldrop, assistant professor of biological sciences at Chapman University, in a statement. “We have assumed that these dogs look different because they are structurally specialized at these tasks, but our study shows that, at least for their skulls, they are not specialized for tasks that involve the skull, such as biting tasks and scent work.”

The research team used advanced scanning technology to create detailed 3D models of dog skulls from museum collections. They mapped key points on each skull—like snout length, jaw structure, and cranial proportions—and compared these measurements across breeds. What they found challenges many common beliefs about working dogs.

“I was most surprised by the overall similarity we see in most of the dog skulls,” admits lead author Nicholas Hebron, who completed the work as a postdoctoral research associate at Chapman University. “Humans have done so much breeding work to alter the visual appearance of these animals that I honestly expected to see really marked groupings of some kind and we really didn’t see much of that.”

When researchers looked specifically at breeds used for scent detection or protection work, they found no distinct skull adaptations that would give these dogs an advantage, though scenting breeds showed some variation within a limited range. They calculated bite-force quotients for different skull types and found no significant differences between breeds historically used for bite work and other breeds of similar size.

This research directly challenges myths about certain breeds being more dangerous than others. “There are many news stories about dogs attacking people badly and often there are specific breeds that are targets of this reporting,” Waldrop notes. “Some people claim these dogs will bite harder than other dogs of the same size, or they have special features like ‘locking jaws’ that make them especially dangerous to people. Our study shows that this is simply not true.”

The only breeds that stood out as truly different were those with extremely short snouts, like Pugs and Bulldogs. These flat-faced breeds have skull shapes unlike any wild canids, suggesting these features came from human preferences rather than functional needs.

These results suggest that successful working dogs aren’t born with specialized equipment. Instead, they’re made through training, temperament, and determination. While we’ve bred dogs to look remarkably different from one another, their skull structures remain surprisingly similar. For organizations selecting working dogs, this means the perfect candidate might not come in the package they expect.

Source : https://studyfinds.org/dog-breed-myth-debunked/

Google might be one of the wealthiest corporations in the world, but that doesn’t mean the multi-trillion-dollar company won’t resort to downsizing.

Over the last year or so, employees in the once-ironclad tech sector have watched in horror as waves of layoffs ravaged their offices and sent wages tumbling.

Bracing for cuts after annual performance reviews on Tuesday, over 1,300 Google employees signed a petition organized by the Alphabet Workers Union (AWU)— the labor union covering Google’s parent corporation, Alphabet — requesting changes to the company’s policy.

Those include guaranteed severance for every laid-off employee, an offer of voluntary layoffs backed by those severance packages, and an end to Google’s performance review system which has pulled double-duty as a mass layoff machine.

“Ongoing rounds of layoffs make us feel insecure about our jobs,” read the petition. “The company is clearly in a strong financial position, making the loss of so many valuable colleagues without explanation hurt even more.”

Google’s response was to turn around and give the petitioners what they asked for. Yesterday, the tech conglomerate announced a “voluntary exit program” for US employees in its Platforms and Devices group — the workers responsible for products like Pixel, Android, Chrome, Fitbit, and Nest. But the AWU notes a one-time offer does not change the long-term employee outlook.

“We are happy to see material progress in response to our concerns,” Google software engineer and AWU union organizing chair Alan McAvinney told Futurism, “but we continue to demand that Google commit to practices like offers of voluntary buyouts and fair terms of severance by codifying them in its actual written policies.”

Source: https://futurism.com/something-bad-inside-google-labor

An official with Meta Platforms’ (META.O), opens new tab popular WhatsApp chat service said Israeli spyware company Paragon Solutions had targeted scores of its users, including journalists and members of civil society.
The official said on Friday that WhatsApp had sent Paragon a cease-and-desist letter following the hack. In a statement, WhatsApp said the company “will continue to protect people’s ability to communicate privately.”Paragon declined to comment.
The WhatsApp official told Reuters it had detected an effort to hack approximately 90 users.
The official declined to say who, specifically, was targeted. But he said those targeted were based in more than two dozen countries, including several people in Europe. He said WhatsApp users were sent malicious electronic documents that required no user interaction to compromise their targets, a so-called zero-click hack that is considered particularly stealthy.

The official said WhatsApp had since disrupted the hacking effort and was referring targets to Canadian internet watchdog group Citizen Lab. The official declined to discuss how it determined that Paragon was responsible for the hack. He said law enforcement and industry partners had been informed, but declined to give details.
The FBI did not immediately return a message seeking comment.
Citizen Lab researcher John Scott-Railton said the discovery of Paragon spyware targeting WhatsApp users “is a reminder that mercenary spyware continues to proliferate and as it does, so we continue to see familiar patterns of problematic use.”

Spyware merchants such as Paragon sell high-end surveillance software to government clients and typically pitch their services as critical to fighting crime and protecting national security.
But such spy tools have repeatedly been discovered on the phones of journalists, activists, opposition politicians, and at least 50 U.S. officials, raising concerns over the unchecked proliferation of the technology.

Source: https://www.reuters.com/technology/cybersecurity/metas-whatsapp-says-israeli-spyware-company-paragon-targeted-scores-users-2025-01-31/

After a phenomenal start on July 26 when bids worth Rs 1.45 lakh crore were received in a single day, the response has been tepid in the following days.

The Centre received bids worth Rs 1,50,130 crore after a total of 37 rounds of bidding in the ongoing 5G Spectrum auction. The auction kicked off on July 26. July 31 saw seven rounds of bidding. At the end of five days, the government had received bids worth Rs 1,49,966 from Reliance Jio and Bharti Airtel. The total bids received on July 30 were to the tune of Rs 111-112 crore.

After a phenomenal start on Tuesday, July 26 when bids worth Rs 1.45 lakh crore were received in a single day, the response has been tepid in the following days. However, after conducting seven fresh rounds of auction on July 30, Saturday, the auction was extended to July 31, Sunday– a departure from the past when the auctions would take place only from Monday to Saturday.

Until July 29, Friday, 71% of the total spectrum put on the block has been sold.

Intense competition in Uttar Pradesh East circle
According to the industry sources, the pitched battle for the 1800 MHz spectrum in Uttar Pradesh East circle seems to be peaking as of now, pointing towards the auction reaching its final stages. Notably, the demand for the Uttar Pradesh East circle after surpassing the supply for the first three days receded below the supply level on July 30.
Earlier, the demand was for 75 blocks against the supply of 54 blocks. However, on July 30, the demand fell to 50 blocks, four less than the available supply in the UP East circle.

Source: https://www.republicworld.com/technology-news/mobile/5g-spectrum-auction-day-6-govt-receives-bids-worth-rs-150130-crore-after-37-rounds-articleshow.html

A Polish scientific institute has categorized domestic cats as an “invasive alien species.”

The Polish Academy of Sciences has defined the house cat (felis catus) as “alien” as it was domesticated in the Middle East and has deemed cats as “invasive” due to the “negative influence of domestic cats on native biodiversity,” they explained in a statement.

The Academy has a long list of animals they deem an “invasive alien species,” including Japanese knotweed, raccoons, clearwing moths, and mandarin ducks.

They state that such species pose “an unpredictable risk to local wildlife,” citing a study showing that cats in Poland kill and eat 48.1 and 583.4 million mammals and 8.9 and 135.7 million birds yearly.

The criteria for including the cat among alien invasive species “are 100% met by the cat,” Wojciech Solarz, a biologist at the state-run Polish Academy of Sciences, told AP.

Cat owners and cat-lovers have expressed outrage at the classification, concerned it will incite the abuse or mistreatment of domestic cats.

Some media reports that given the false impression that the institute was calling for feral and other cats to be euthanized, AP reported.

Comments on the Academy’s Facebook page see people saying the institution’s classification is “simply stupid and harmful,” with one saying, ” you suck and are unworthy of your name.”