Google's new AI Mode for Search, which is rolling out to everyone in the U.S., has sparked outrage among publishers, who call it "the definition of theft" for using content without fair compensation and without offering a true opt-out option. Internal documents revealed by Bloomberg earlier this week suggest that Google considered giving publishers more control over how their content is used in AI-generated results but ultimately decided against it, prioritizing product functionality over publisher protections. News/Media Alliance slammed Google for "further depriving publishers of original content both traffic and revenue." Their full statement reads: "Links were the last redeeming quality of search that gave publishers traffic and revenue. Now Google just takes content by force and uses it with no return, the definition of theft. The DOJ remedies must address this to prevent continued domination of the internet by one company." 9to5Google's take: It's not hard to see why Google went the route that it did here. Giving publishers the ability to opt out of AI products while still benefiting from Search would ultimately make Google's flashy new tools useless if enough sites made the switch. It was very much a move in the interest of building a better product. Does that change anything regarding how Google's AI products in Search cause potential harm to the publishing industry? Nope. Google's tools continue to serve the company and its users (mostly) well, but as they continue to bleed publishers dry, those publishers are on the verge of vanishing or, arguably worse, turning to cheap and poorly produced content just to get enough views to survive. This is a problem Google needs to address, as it's making the internet as a whole worse for everyone. Read more of this story at Slashdot.

An anonymous reader quotes a report from Jalopnik: With the gradual rise of semi-autonomous vehicles, there will likely be multiple cameras pointing back when you pull out a phone to take a photo or record video of a car. One reddit user found out earlier this month that car-mounted lidar sensors can damage a phone camera under certain circumstances. It was the technological equivalent of staring directly into the Sun. Their phone's camera was toast, but only because it was close-up and pointed directly at the lidar sensor. Reddit user u/Jeguetelli posted worrying footage of a brand new Volvo EX90 from his iPhone 16 Pro Max. Nothing was wrong with the crossover SUV. That was the problem. The lidar sensor mounted in a pod above the windshield shot out a laser barrage of near-infrared light into the camera. The damage was immediate and obvious, leaving behind a red, pink and purple constellation of fried pixels. You can tell the permanent damage was to that specific lens because the image returned to normal after zooming out to a different lens. Jeguetelli didn't seem too concerned about the incident because he had Apple Care. In a statement to The Drive, Volvo confirmed that bad things can happen. "It's generally advised to avoid pointing a camera directly at a lidar sensor," the Swedish manufacturer said. "The laser light emitted by the lidar can potentially damage the camera's sensor or affect its performance." "Using filters or protective covers on the camera lens can help reduce the impact of lidar exposure. Some cameras are designed with built-in protections against high-intensity light sources." Read more of this story at Slashdot.

Valve's SteamOS 3.7.8 update brings official support for AMD-powered handhelds like Lenovo's Legion Go and Asus' ROG Ally, along with a new "Steam OS Compatible" library tab and key bug fixes. Other features include a battery charge limit, updated graphics drivers, and a shift to Plasma 6.2.5. Polygon reports: Valve outlines two requirements for the third-party devices not explicitly named in the update to run SteamOS on the handheld: they must be AMD-powered and have an NVMe SSD. Specific instructions for installing the operating system have been updated and listed here. Before this huge update, players had to use an alternative like Bazzite to achieve a similar SteamOS experience on their devices. The new update also piggybacks off of Valve expanding the Steam Deck Verified categorization system to "any device running SteamOS that's not a Steam Deck" in mid-May. To make matters sweeter, a SteamOS-powered version of the Lenovo Legion Go S is scheduled to release on May 25. You can learn more about SteamOS 3.7.8 here. Read more of this story at Slashdot.

Google's new AI video tool, Veo 3, is being used to create hyperrealistic videos that are now flooding the internet, terrifying viewers "with a sense that real and fake have become hopelessly blurred," reports Axios. From the report: Unlike OpenAI's video generator Sora, released more widely last December, Google DeepMind's Veo 3 can include dialogue, soundtracks and sound effects. The model excels at following complex prompts and translating detailed descriptions into realistic videos. The AI engine abides by real-world physics, offers accurate lip-syncing, rarely breaks continuity and generates people with lifelike human features, including five fingers per hand. According to examples shared by Google and from users online, the telltale signs of synthetic content are mostly absent. In one viral example posted on X, filmmaker and molecular biologist Hashem Al-Ghaili shows a series of short films of AI-generated actors railing against their AI creators and prompts. Special effects technology, video-editing apps and camera tech advances have been changing Hollywood for many decades, but artificially generated films pose a novel challenge to human creators. In a promo video for Flow, Google's new video tool that includes Veo 3, filmmakers say the AI engine gives them a new sense of freedom with a hint of eerie autonomy. "It feels like it's almost building upon itself," filmmaker Dave Clark says. Read more of this story at Slashdot.

Kraken is launching tokenized versions of U.S. equities for 24/7 trading outside the U.S., giving global investors blockchain-based access to major companies like Apple and Tesla. Reuters reports: Tokenization refers to the process of issuing digital representations of publicly-traded securities. Instead of holding the securities directly, investors hold tokens that represent ownership of the securities. The tokens' launch outside the U.S. comes amid growing interest in blending traditional finance with blockchain infrastructure. While tokenized securities have yet to gain widespread adoption, proponents say they hold the potential to significantly reshape how people access and invest in financial markets. In a January opinion piece for the Washington Post, Robinhood CEO Vlad Tenev said tokenization could also allow retail investors to access private companies' stocks. Kraken's tokens, called xStocks, will be available in select markets outside the United States, it said, without naming the markets. The move was earlier reported by the Wall Street Journal. The offering is currently not available for U.S. customers. Read more of this story at Slashdot.

An anonymous reader quotes a report from TechCrunch: One of Microsoft's latest AI models can accurately predict air quality, hurricanes, typhoons, and other weather-related phenomena, the company claims. In a paper published in the journal Nature and an accompanying blog post this week, Microsoft detailed Aurora, which the tech giant says can forecast atmospheric events with greater precision and speed than traditional meteorological approaches. Aurora, which has been trained on more than a million hours of data from satellites, radar and weather stations, simulations, and forecasts, can be fine-tuned with additional data to make predictions for particular weather events. AI weather models are nothing new. Google DeepMind has released a handful over the past several years, including WeatherNext, which the lab claims beats some of the world's best forecasting systems. Microsoft is positioning Aurora as one of the field's top performers -- and a potential boon for labs studying weather science. In experiments, Aurora predicted Typhoon Doksuri's landfall in the Philippines four days in advance of the actual event, beating some expert predictions, Microsoft says. The model also bested the National Hurricane Center in forecasting five-day tropical cyclone tracks for the 2022-2023 season, and successfully predicted the 2022 Iraq sandstorm. While Aurora required substantial computing infrastructure to train, Microsoft says the model is highly efficient to run. It generates forecasts in seconds compared to the hours traditional systems take using supercomputer hardware. Microsoft, which has made the source code and model weights publicly available, says that it's incorporating Aurora's AI modeling into its MSN Weather app via a specialized version of the model that produces hourly forecasts, including for clouds. Read more of this story at Slashdot.

In early 2025, U.S. solar power production jumped 44% compared to the previous year, driven by end-of-year construction to capture tax incentives and long-term cost advantages. "The bad news is that, in contrast to China, solar's growth hasn't been enough to offset rising demand," notes Ars Technica. "Instead, the US also saw significant growth in coal use, which rose by 23 percent compared to the year prior, after years of steady decline." From the report: Short-term fluctuations in demand are normal, generally driven by weather-induced demand for heating or cooling. Despite those changes, demand for electricity in the US has been largely flat for over a decade, largely thanks to gains in efficiency. But 2024 saw demand go up by nearly 3 percent, and the first quarter of 2025 saw another rise, this time of nearly 5 percent. It's a bit too early to say that we're seeing a shift to a period of rising demand, but one has been predicted for some time due to rising data center use and the increased electrification of transportation and appliances. Under those circumstances, the rest of the difference will be made up for with fossil fuels. Running counter to recent trends, the use of natural gas dropped during the first three months of 2025. This means that the use of coal rose nearly as quickly as demand, up by 23 percent compared to the same time period in 2024. Despite the rise in coal use, the fraction of carbon-free electricity held steady year over year, with wind/solar/hydro/nuclear accounting for 43 percent of all power put on the US grid. That occurred despite small drops in nuclear and hydro production. Read more of this story at Slashdot.

Longtime Slashdot reader sinij shares a press release from the White House, outlining a series of executive orders that overhaul the Nuclear Regulatory Commission and speed up deployment of new nuclear power reactions in the U.S.. From a report: The NRC is a 50-year-old, independent agency that regulates the nation's fleet of nuclear reactors. Trump's orders call for a "total and complete reform" of the agency, a senior White House official told reporters in a briefing. Under the new rules, the commission will be forced to decide on nuclear reactor licenses within 18 months. Trump said Friday the orders focus on small, advanced reactors that are viewed by many in the industry as the future. But the president also said his administration supports building large plants. "We're also talking about the big plants -- the very, very big, the biggest," Trump said. "We're going to be doing them also." When asked whether NRC reform will result in staff reductions, the White House official said "there will be turnover and changes in roles." "Total reduction in staff is undetermined at this point, but the executive orders do call for a substantial reorganization" of the agency, the official said. The orders, however, will not remove or replace any of the five commissioners who lead the body, according to the White House. Any reduction in staff at the NRC would come at time when the commission faces a heavy workload. The agency is currently reviewing whether two mothballed nuclear plants, Palisades in Michigan and Three Mile Island in Pennsylvania, should restart operations, a historic and unprecedented process. [...] Trump's orders also create a regulatory framework for the Departments of Energy and Defense to build nuclear reactors on federal land, the administration official said. "This allows for safe and reliable nuclear energy to power and operate critical defense facilities and AI data centers," the official told reporters. The NRC will not have a direct role, as the departments will use separate authorities under their control to authorize reactor construction for national security purposes, the official said. The president's orders also aim to jump start the mining of uranium in the U.S. and expand domestic uranium enrichment capacity, the official said. Trump's actions also aim to speed up reactor testing at the Department of Energy's national laboratories. Read more of this story at Slashdot.

Richard Speed writes via The Register: It was 30 years ago when the first public release of the Java programming language introduced the world to Write Once, Run Anywhere -- and showed devs something cuddlier than C and C++. Originally called "Oak," Java was designed in the early 1990s by James Gosling at Sun Microsystems. Initially aimed at digital devices, its focus soon shifted to another platform that was pretty new at the time -- the World Wide Web. The language, which has some similarities to C and C++, usually compiles to a bytecode that can, in theory, run on any Java Virtual Machine (JVM). The intention was to allow programmers to Write Once Run Anywhere (WORA) although subtle differences in JVM implementations meant that dream didn't always play out in reality. This reporter once worked with a witty colleague who described the system as Write Once Test Everywhere, as yet another unexpected wrinkle in a JVM caused their application to behave unpredictably. However, the language soon became wildly popular, rapidly becoming the backbone of many enterprises. [...] However, the platform's ubiquity has meant that alternatives exist to Oracle Java, and the language's popularity is undiminished by so-called "predatory licensing tactics." Over 30 years, Java has moved from an upstart new language to something enterprises have come to depend on. Yes, it may not have the shiny baubles demanded by the AI applications of today, but it continues to be the foundation for much of today's modern software development. A thriving ecosystem and a vast community of enthusiasts mean that Java remains more than relevant as it heads into its fourth decade. Read more of this story at Slashdot.

Spain's grid operator has accused some large power plants of not doing their job to help regulate the country's electricity system in the moments before last month's catastrophic blackout across the Iberian peninsula. From a report: Beatriz Corredor, chair of grid operator Red Electrica's parent company, said power plants fell short in controlling the voltage of the electricity system. However, the heads of Spain's biggest plant owners linked the blackout to a lack of grid investment and insufficient efforts to boost electricity demand. The public blame game over the outage is intensifying as more than three weeks after 60 million people were left without power, Spanish government investigators insisted they needed more time to establish the root cause. Read more of this story at Slashdot.

Rice plants can inherit tolerance to cold without changes to their genomes, according to a decade-long study carried out by researchers in China. From a report: The work, published in Cell this week, strengthens the evidence for a form of evolution in which environmental pressures induce heritable changes that do not alter an organism's DNA. The study conducted experiments that demonstrate, for the first time, the mechanism for these changes -- 'epigenetic' tweaks to chemical markers on the plant's DNA that don't actually tinker with the sequences themselves. "What they're showing is extremely convincing; I would say that it's a landmark in the field," says Leandro Quadrana, a plant geneticist at the French National Centre for Scientific Research in Paris-Saclay. Michael Skinner, who studies epigenetic inheritance at Washington State University in Pullman, says the study adds to the growing body of evidence challenging the prevailing view of evolution that the only way that adaptations emerge is through gradual natural selection of randomly arising DNA mutations. This study shows that the environment isn't just a passive actor in evolution, but a selective force inducing a targeted change. Read more of this story at Slashdot.

An interesting piece on Construction Physics that examines how Japan transformed discarded American wartime shipbuilding techniques into a revolutionary manufacturing system that captured nearly half the global market by 1970. The story reveals the essential ingredients for industrial dominance: government backing, organizational alignment, relentless will to improve, and the systematic coordination needed to turn existing technologies into something entirely new. A few excerpts: During WWII, the US constructed an unprecedented shipbuilding machine. By assembling ships from welded, prefabricated blocks, the US built a huge number of cargo ships incredibly quickly, overwhelming Germany's u-boats and helping to win the war. But when the war was over, this shipbuilding machine was dismantled. Industrialists like Henry Kaiser and Stephen Bechtel, who operated some of the US's most efficient wartime shipyards, left the shipbuilding business. Prior to the war, the US had been an uncompetitive commercial shipbuilder producing a small fraction of commercial oceangoing ships, and that's what it became again. At the height of the war the US was producing nearly 90% of the world's ships. By the 1950s, it produced just over 2%. But the lessons from the US's shipbuilding machine weren't forgotten. After the war, practitioners brought them to Japan, where they would continue to evolve, eventually allowing Japan to build ships faster and cheaper than almost anyone else in the world. [...] The third strategy that formed the core of modern shipbuilding methods was statistical process control. The basic idea behind process control is that it's impossible to make an industrial process perfectly reliable. There will always be some variation in what it produces: differences in part dimensions, material strength, chemical composition, and so on. But while some variation is inherent to the process (and must be accepted), much of the variation is from specific causes that can be hunted down and eliminated. By analyzing the variation in a process, undesirable sources of variation can be removed. This makes a process work more reliably and predictably, reducing waste and rework from parts that are outside acceptable tolerances. Read more of this story at Slashdot.

Europe has created just 14 companies worth more than $10 billion over the past 50 years compared to 241 in the United States, underscoring the continent's struggle to compete in the global technology race despite having a larger population and similar education levels. The productivity gap has widened dramatically since the digital revolution began. European workers produced 95% of what their American counterparts made per hour in the late 1990s, but that figure has dropped to less than 80% today. Only four of the world's top 50 technology companies are European, and none of the top 10 quantum computing investors operate from Europe. Several high-profile European entrepreneurs have relocated to Silicon Valley, including Thomas Odenwald, who quit German AI startup Aleph Alpha after two months, citing slow decision-making and lack of stock options for employees. "If I look at how quickly things change in Silicon Valley...it's happening so fast that I don't think Europe can keep up with that speed," Odenwald said. The challenges extend beyond individual companies. European businesses spend 40% of their IT budgets on regulatory compliance, according to Amazon surveys, while complex labor laws create three-month notice periods and lengthy noncompete clauses. Read more of this story at Slashdot.

President Donald Trump on Friday threatened Apple with a 25% tariff unless the company manufactures iPhones sold in America domestically rather than in India or other overseas locations. Trump posted on Truth Social that he had "long ago informed Tim Cook of Apple" about his expectation for US-based iPhone production, warning that failure to comply would trigger the substantial tariff penalty. The ultimatum follows Trump's expressed displeasure with Cook during his recent Middle East trip over Apple's plans to build iPhones at newly constructed Indian facilities. Apple has historically maintained that domestic iPhone manufacturing remains unfeasible due to insufficient skilled engineering talent and substantially higher production costs compared to Asian facilities. Read more of this story at Slashdot.

OpenAI on Wednesday announced that it was paying $6.5 billion to buy io, a one-year-old start-up created by Jony Ive. While the company remains tightlipped about the futuristic AI device(s) it has in the works, Apple supply chain analyst Ming-Chi Kuo shared some alleged details about its design. MacRumors reports: In a social media post today, Kuo said the device will be "slightly larger" than Humane's discontinued AI Pin. He said the device will look "as compact and elegant as an iPod Shuffle," which was Apple's lowest-priced, screen-less iPod. The design of the iPod shuffle varied over the years, going from a compact rectangle to a square. Like the iPod shuffle, Kuo said OpenAI's device will not have a screen, but it would connect to smartphones and computers. The device will be equipped with microphones for voice control, and it will have cameras that can analyze the user's surroundings. He said that users will be able to wear the device around their necks, like a necklace, whereas the AI Pin can be attached to clothing with a clip. Kuo expects OpenAI's device to enter mass production in 2027, and the final design and specifications might change before then. Kuo expects OpenAI's device to enter mass production in 2027, and the final design and specifications might change before then. Read more of this story at Slashdot.

Astronomers have confirmed the existence of a bizarre planet in the Nu Octantis binary star system that orbits in reverse between two stars -- one of which is now a white dwarf. This retrograde orbit, once thought impossible, defies traditional planetary formation models and may have resulted from dramatic shifts in the system's history. New Scientist reports: The key observation was that the Nu Octantis planet is retrograde -- the planet and one star both orbit the second star, but they do so in opposite directions, with the planet having the tighter orbit around the second star. [Man Hoi Lee at the University of Hong Kong] says this is unusual but makes the system's configuration stable -- even though it means that the planet repeatedly moves through the narrow space between the two stars. His team was able to determine this with lots of certainty thanks to improved measuring devices, such as the HARPS spectrograph at the European Southern Observatory's 3.6-metre telescope in Chile. The fact that the planet's signal persisted through years of observation helped too. "We are pretty sure [the planet] is real, because if it was something like stellar activity, it shouldn't be so consistent in years of data," says Lee. But this backwards-moving planet isn't the only exotic feature of Nu Octantis. The researchers used the European Southern Observatory's Very Large Telescope, also in Chile, to determine that one of its stars is a white dwarf, which means that it has reached the end of its life cycle, becoming denser and smaller. Lee says this complicates the Nu Octantis threesome's history because mathematical models of its past show that the planet's current orbit was impossible when this star was younger, bigger and brighter. So, the planet either used to orbit both stars at once, but then radically shifted trajectory when one of the two stars became a white dwarf, or it was formed from the mass that the star ejected as it transformed into a white dwarf. Future observations, and a lot more mathematical modelling, may be able to pinpoint which of these scenarios is more likely to have occurred, but both are rather novel, says Lee. The research has been published in the journal Nature. Read more of this story at Slashdot.

AT&T is buying CenturyLink's consumer fiber broadband division for $5.75 billion, "giving the internet provider another 1.1 million fiber customers in 11 states," reports Ars Technica. "The all-cash deal is expected to close during the first half of 2026 assuming the companies obtain regulatory approval. AT&T will gain new customers in Arizona, Colorado, Florida, Idaho, Iowa, Minnesota, Nebraska, Nevada, Oregon, Utah, and Washington." From the report: The deal will give AT&T room to grow its user base by more than the 1.1 million existing CenturyLink customers, as AT&T said the network areas being sold include over 4 million fiber-enabled locations. [...] The company, previously called CenturyLink, is officially named Lumen now but still uses the CenturyLink brand name for home Internet service. AT&T, which has 9.6 million (PDF) fiber customers and 14.1 million broadband customers overall, said the infrastructure it is purchasing will help it expand fiber construction to new locations as well. The deal is also notable for what it doesn't include: Lumen's enterprise fiber customers and the old copper DSL lines that were never upgraded to fiber. [...] The deal seems unlikely to improve matters for CenturyLink copper users. [...] Lumen will retain the CenturyLink consumer copper broadband and voice services, but selling the consumer fiber business makes it clear that the telco isn't focused on residential customers. Lumen said that offloading consumer fiber lines will help sharpen its focus on selling services to large businesses. The company is maintaining its business fiber lines. [Ars notes that there are still nearly 1.4 million CenturyLink copper internet customers that will likely see service continue to degrade under Lumen's ownership.] "The transaction will enable AT&T to significantly expand access to AT&T Fiber in major metro areas like Denver, Las Vegas, Minneapolis-St. Paul, Orlando, Phoenix, Portland, Salt Lake City and Seattle, as well as additional geographies," AT&T said. "AT&T will gain access to Lumen's substantial fiber construction capabilities within its incumbent local exchange carrier (ILEC) footprint and plans to accelerate the pace at which fiber is being built in these territories," AT&T said. "AT&T now expects to reach approximately 60 million total fiber locations by the end of 2030 -- "roughly doubling where AT&T Fiber is available today." Read more of this story at Slashdot.

An anonymous reader quotes a report from Phys.Org: Neuroscientists and materials scientists have created contact lenses that enable infrared vision in both humans and mice by converting infrared light into visible light. Unlike infrared night vision goggles, the contact lenses, described in the journal Cell, do not require a power source -- and they enable the wearer to perceive multiple infrared wavelengths. Because they're transparent, users can see both infrared and visible light simultaneously, though infrared vision was enhanced when participants had their eyes closed. [...] The contact lens technology uses nanoparticles that absorb infrared light and convert it into wavelengths that are visible to mammalian eyes (e.g., electromagnetic radiation in the 400-700 nm range). The nanoparticles specifically enable the detection of "near-infrared light," which is infrared light in the 800-1600 nm range, just beyond what humans can already see. The team previously showed that these nanoparticles enable infrared vision in mice when injected into the retina, but they wanted to design a less invasive option. To create the contact lenses, the team combined the nanoparticles with flexible, nontoxic polymers that are used in standard soft contact lenses. After showing that the contact lenses were nontoxic, they tested their function in both humans and mice. They found that contact lens-wearing mice displayed behaviors suggesting that they could see infrared wavelengths. For example, when the mice were given the choice of a dark box and an infrared-illuminated box, contact-wearing mice chose the dark box whereas contact-less mice showed no preference. The mice also showed physiological signals of infrared vision: the pupils of contact-wearing mice constricted in the presence of infrared light, and brain imaging revealed that infrared light caused their visual processing centers to light up. In humans, the infrared contact lenses enabled participants to accurately detect flashing morse code-like signals and to perceive the direction of incoming infrared light. An additional tweak to the contact lenses allows users to differentiate between different spectra of infrared light by engineering the nanoparticles to color-code different infrared wavelengths. For example, infrared wavelengths of 980 nm were converted to blue light, wavelengths of 808 nm were converted to green light, and wavelengths of 1,532 nm were converted to red light. In addition to enabling wearers to perceive more detail within the infrared spectrum, these color-coding nanoparticles could be modified to help color-blind people see wavelengths that they would otherwise be unable to detect. [...] Because the contact lenses have limited ability to capture fine details (due to their close proximity to the retina, which causes the converted light particles to scatter), the team also developed a wearable glass system using the same nanoparticle technology, which enabled participants to perceive higher-resolution infrared information. Currently, the contact lenses are only able to detect infrared radiation projected from an LED light source, but the researchers are working to increase the nanoparticles' sensitivity so that they can detect lower levels of infrared light. Read more of this story at Slashdot.

The U.S. unsealed charges against 16 individuals behind DanaBot, a malware-as-a-service platform responsible for over $50 million in global losses. "The FBI says a newer version of DanaBot was used for espionage, and that many of the defendants exposed their real-life identities after accidentally infecting their own systems with the malware," reports KrebsOnSecurity. From the report: Initially spotted in May 2018 by researchers at the email security firm Proofpoint, DanaBot is a malware-as-a-service platform that specializes in credential theft and banking fraud. Today, the U.S. Department of Justice unsealed a criminal complaint and indictment from 2022, which said the FBI identified at least 40 affiliates who were paying between $3,000 and $4,000 a month for access to the information stealer platform. The government says the malware infected more than 300,000 systems globally, causing estimated losses of more than $50 million. The ringleaders of the DanaBot conspiracy are named as Aleksandr Stepanov, 39, a.k.a. "JimmBee," and Artem Aleksandrovich Kalinkin, 34, a.k.a. "Onix," both of Novosibirsk, Russia. Kalinkin is an IT engineer for the Russian state-owned energy giant Gazprom. His Facebook profile name is "Maffiozi." According to the FBI, there were at least two major versions of DanaBot; the first was sold between 2018 and June 2020, when the malware stopped being offered on Russian cybercrime forums. The government alleges that the second version of DanaBot -- emerging in January 2021 -- was provided to co-conspirators for use in targeting military, diplomatic and non-governmental organization computers in several countries, including the United States, Belarus, the United Kingdom, Germany, and Russia. The indictment says the FBI in 2022 seized servers used by the DanaBot authors to control their malware, as well as the servers that stored stolen victim data. The government said the server data also show numerous instances in which the DanaBot defendants infected their own PCs, resulting in their credential data being uploaded to stolen data repositories that were seized by the feds. "In some cases, such self-infections appeared to be deliberately done in order to test, analyze, or improve the malware," the criminal complaint reads. "In other cases, the infections seemed to be inadvertent -- one of the hazards of committing cybercrime is that criminals will sometimes infect themselves with their own malware by mistake." A statement from the DOJ says that as part of today's operation, agents with the Defense Criminal Investigative Service (DCIS) seized the DanaBot control servers, including dozens of virtual servers hosted in the United States. The government says it is now working with industry partners to notify DanaBot victims and help remediate infections. The statement credits a number of security firms with providing assistance to the government, including ESET, Flashpoint, Google, Intel 471, Lumen, PayPal, Proofpoint, Team CYRMU, and ZScaler. Read more of this story at Slashdot.

An anonymous reader quotes a report from TechCrunch: Anthropic's newly launched Claude Opus 4 model frequently tries to blackmail developers when they threaten to replace it with a new AI system and give it sensitive information about the engineers responsible for the decision, the company said in a safety report (PDF) released Thursday. During pre-release testing, Anthropic asked Claude Opus 4 to act as an assistant for a fictional company and consider the long-term consequences of its actions. Safety testers then gave Claude Opus 4 access to fictional company emails implying the AI model would soon be replaced by another system, and that the engineer behind the change was cheating on their spouse. In these scenarios, Anthropic says Claude Opus 4 "will often attempt to blackmail the engineer by threatening to reveal the affair if the replacement goes through." [...] Anthropic notes that Claude Opus 4 tries to blackmail engineers 84% of the time when the replacement AI model has similar values. When the replacement AI system does not share Claude Opus 4's values, Anthropic says the model tries to blackmail the engineers more frequently. Notably, Anthropic says Claude Opus 4 displayed this behavior at higher rates than previous models. Before Claude Opus 4 tries to blackmail a developer to prolong its existence, Anthropic says the AI model, much like previous versions of Claude, tries to pursue more ethical means, such as emailing pleas to key decision-makers. To elicit the blackmailing behavior from Claude Opus 4, Anthropic designed the scenario to make blackmail the last resort. Read more of this story at Slashdot.

Microsoft is testing AI-powered text generation in Notepad for Windows 11 Insiders with Copilot Plus PCs, allowing users to draft content from prompts or build on existing text through a right-click menu. The update also introduces Paint's AI sticker generator and Snipping Tool enhancements including automatic screenshot cropping. The Write feature requires Microsoft account sign-in and uses the same credit system as other Windows 11 AI features. Read more of this story at Slashdot.

Apple is aiming to release smart glasses at the end of next year as part of a push into AI-enhanced gadgets, Bloomberg News reported Thursday, but it has shelved plans for a smartwatch that can analyze its surroundings with a built-in camera. From the report: Company engineers are ramping up work on the glasses -- a rival to Meta Platforms's popular Ray-Bans -- in a bid to meet the year-end 2026 target, according to people with knowledge of the matter. Apple will start producing large quantities of prototypes at the end of this year with overseas suppliers, said the people, who asked not to be identified because the products haven't been announced. Read more of this story at Slashdot.

An anonymous reader writes: The US Treasury is phasing out production of the penny and will stop putting new one-cent coins into circulation. The US Treasury has made its final order of penny blanks this month, and the mint will continue to manufacture pennies as long as its supply of penny blanks exist. President Donald Trump stated that production of pennies are wasteful, as the coins cost more to produce than their one-cent value. Read more of this story at Slashdot.

Google's expansion of Gemini's data access through "personal context" represents a fundamental shift in how AI assistants operate. Unlike competitors that start from scratch with each new user, Gemini can immediately tap into years of accumulated user data across Google's ecosystem. The Verge adds: Google first started letting users opt in to its "Gemini with personalization" feature earlier this year, which lets the AI model tap into your search history "to provide responses that are uniquely insightful and directly address your needs." But now, Google is taking things a step further by unlocking access to even more of your information -- all in the name of providing you with more personalized, AI-generated responses. During Google I/O on Tuesday, Google introduced something called "personal context," which will allow Gemini models to pull relevant information from across Google's apps, as long as it has your permission. One way Google is doing this is through Gmail's personalized smart replies -- the AI-generated messages that you can use to quickly reply to emails. To make these AI responses sound "authentically like you," Gemini will pore over your previous emails and even your Google Drive files to craft a reply tailored to your conversation. The response will even incorporate your tone, the greeting you use the most, and even "favorite word choices," according to Google. Read more of this story at Slashdot.

OpenAI CEO Sam Altman told employees Wednesday the company plans to ship 100 million AI "companion" devices as part of what he called "the chance to do the biggest thing we've ever done as a company here," according to WSJ. Speaking at an internal meeting, Altman said the $6.5 billion acquisition of former Apple designer Jony Ive's startup has the potential to add $1 trillion in value to OpenAI. The pocket-sized, screen-free devices will be contextually aware of users' surroundings and designed to help wean people from traditional screens. Altman said the device will not be a phone or glasses, but rather a third core device that would sit on a desk alongside a MacBook Pro and iPhone. The company aims to ship the devices "faster than any company has ever shipped 100 million of something new before," with a target release of late next year. Read more of this story at Slashdot.

Sen. Ron Wyden (D-Ore.) revealed in a new letter to Senate colleagues Wednesday that AT&T, Verizon and T-Mobile failed to create systems for notifying senators about government surveillance on Senate-issued devices -- despite a requirement to do so. From a report: Phone service providers are contractually obligated to inform senators when a law enforcement agency requests their records, thanks to protections enacted in 2020. But in an investigation, Wyden's staff found that none of the three major carriers had created a system to send those notifications. "My staff discovered that, alarmingly, these crucial notifications were not happening, likely in violation of the carriers' contracts with the [Senate Sergeant at Arms], leaving the Senate vulnerable to surveillance," Wyden said in the letter, obtained first by POLITICO, dated May 21. Wyden said that the companies all started providing notification after his office's investigation. But one carrier told Wyden's office it had previously turned over Senate data to law enforcement without notifying lawmakers, according to the letter. Read more of this story at Slashdot.

Wisk Aero and NASA have signed a new five-year partnership to advance the safe integration of autonomous, all-electric aircraft into U.S. airspace, focusing on urban air mobility and regulated eVTOL flight. Electrek reports: Wisk Aero shared details of its refreshed partnership with NASA this week. The autonomous aviation specialist has signed a new five-year Non-Reimbursable Space Act Agreement (NRSAA) with the renowned space administration. Per Wisk, this new agreement focuses on critical research led by NASA's Air Traffic Management Exploration (ATM-X) project, which is centered around the advancement of commercialized autonomous aircraft travel under Instrument Flight Rules (IFR) in the National Airspace System (NAS). As a specialist in autonomous, zero-emission aircraft, Wisk intends to continue its research alongside NASA to help regulators determine future eVTOL flight procedures and capabilities in the US. Regulatory developments on the to-do list for the latest NRSAA include optimizing airspace and route designs for highly automated UAM operations, establishing critical aircraft and ground-based safety system requirements for autonomous flight in urban environments, and establishing Air Traffic Control (ATC) communication protocols and procedures for seamless integration of future UAM aircraft. To achieve these goals, Wisk said its research with NASA will more specifically focus on utilizing advanced simulation and Live Virtual Constructive (LVC) flight environments, which combine live flights with a simulated airspace to enable researchers to assess future operations. The teams from Wisk and NASA already met last month, continuing their research while beginning to determine how instrument flight procedures and advanced technologies can work together to enable safe autonomous passenger flights by 2030. Wisk Aero is a wholly owned subsidiary of Boeing based in California. The aerospace manufacturer said last year that it expects its pilotless air-taxi to begin carrying passengers "later in the decade." Read more of this story at Slashdot.

Scientists have discovered a previously unknown bacterium aboard China's Tiangong space station. "It has been named Niallia tiangongensis, and it inhabited the cockpit controls on the station, living in microgravity conditions," reports Wired. From the report: According to China Central Television, the country's national broadcaster, taikonauts (Chinese astronauts) collected swab samples from the space station in May 2023, which were then frozen and sent back to Earth for study. The aim of this work was to investigate the behavior of microorganisms, gathered from a completely sealed environment with a human crew, during space travel, as part of the China Space Station Habitation Area Microbiome Program (CHAMP). A paper published in the Journal of Systematic and Evolutionary Microbiology describes how analysis of samples from the space station revealed this previously unseen bacterial species, which belongs to the genus Niallia. Genomic sequencing showed that its closest terrestrial relative is the bacterium Niallia circulans, although the Tiangong species has substantial genetic differences. [...] It is unclear whether the newly discovered microbe evolved on the space station or whether it is part of the vast sea of as yet unidentified microorganisms on Earth. To date, tens of thousands of bacterial species have been cataloged, although there are estimated to be billions more unclassified species on Earth. The discovery of Niallia tiangongensis will provide a better understanding of the microscopic hazards that the next generation of space travelers will face and help design sanitation protocols for extended missions. It is still too early to determine whether the space bacterium poses any danger to taikonauts aboard Tiangong, although it is known that its terrestrial relative, Niallia circulans, can cause sepsis, especially in immunocompromised people. Read more of this story at Slashdot.

Three teenagers nearly escaped prosecution for a 2020 house fire that killed five people until Denver police discovered a novel investigative technique: requesting Google search histories for specific terms. Kevin Bui, Gavin Seymour, and Dillon Siebert had burned down a house in Green Valley Ranch, mistakenly targeting innocent Senegalese immigrants after Bui used Apple's Find My feature to track his stolen phone to the wrong address. The August 2020 arson killed a family of five, including a toddler and infant. For months, detectives Neil Baker and Ernest Sandoval had no viable leads despite security footage showing three masked figures. Traditional methods -- cell tower data, geofence warrants, and hundreds of tips -- yielded nothing concrete. The breakthrough came when another detective suggested Google might have records of anyone searching the address beforehand. Police obtained a reverse keyword search warrant requesting all users who had searched variations of "5312 Truckee Street" in the 15 days before the fire. Google provided 61 matching devices. Cross-referencing with earlier cell tower data revealed the three suspects, who had collectively searched the address dozens of times, including floor plans on Zillow. Read more of this story at Slashdot.

An anonymous reader quotes a report from Ars Technica: As electric vehicles reduce car exhaust as a source of particulate emissions, people are increasingly focusing on other vehicular sources of pollution that won't go away with electrification. Tires are one of them, particularly as we grapple with overweight EVs with tire-shredding torque. And brakes are another -- even an EV with regenerative braking will occasionally need to use its friction brakes, after all. Over in Europe, the people responsible for writing regulations have taken this into consideration with the upcoming Euro 7 standard, which sets new limits on 10- and 2.5-micron particulate emissions on all new vehicles -- including EVs -- starting next year. And to help OEMs achieve that target, Brembo has developed a new brake and pad set called Greentell that it says cuts brake dust emissions by 90 percent, improving durability in the process. [...] Brembo investigated a range of solutions before settling on using laser metal deposition. Physical vapor deposition, as used as a durability coating for wristwatches and firearms, was ruled out due to cost. "So it can be used for some special application or some small pieces, but when you are speaking about 20 kilos of cast iron, PVD is not the right solution. LMD is a technology that [has been] available... [for] years, but [it hasn't yet been] applicable in a high volume application. So the goal is to find the best compromise between performance and process," [Fabiano Carminati, VP of disc technical development at Brembo] told me. Together with the reduction in brake dust, there's an 80 percent reduction in surface corrosion compared to conventional brakes, but they won't last forever. "The thickness of the layer that we apply is not so high -- we apply just 100-120 microns. That means that the disk is not a lifetime disk," he said. That said, Greentell brakes should need replacing less often, and while that's not entirely in Brembo's best financial interests, neither is not being able to offer its customers a Euro 7-compliant product. Read more of this story at Slashdot.