AmiMoJo writes: The Shenzhen 8K UHD Video Industry Cooperation Alliance, a group made up of more than 50 Chinese companies, just released a new wired media communication standard called the General Purpose Media Interface or GPMI. This standard was developed to support 8K and reduce the number of cables required to stream data and power from one device to another. According to HKEPC, the GPMI cable comes in two flavors -- a Type-B that seems to have a proprietary connector and a Type-C that is compatible with the USB-C standard. Because 8K has four times the number of pixels of 4K and 16 times more pixels than 1080p resolution, it means that GPMI is built to carry a lot more data than other current standards. There are other variables that can impact required bandwidth, of course, such as color depth and refresh rate. The GPMI Type-C connector is set to have a maximum bandwidth of 96 Gbps and deliver 240 watts of power. This is more than double the 40 Gbps data limit of USB4 and Thunderbolt 4, allowing you to transmit more data on the cable. However, it has the same power limit as that of the latest USB Type-C connector using the Extended Power Range (EPR) standard. GPMI Type-B beats all other cables, though, with its maximum bandwidth of 192 Gbps and power delivery of up to 480 watts.

Read more of this story at Slashdot.

An anonymous reader shares a report: Waymo is preparing to use data from its robotaxis, including video from interior cameras tied to rider identities, to train generative AI models, according to an unreleased version of its privacy policy found by researcher Jane Manchun Wong. The draft language reveals Waymo may also share this data to personalize ads, raising fresh questions about how much of a rider's behavior inside autonomous vehicles could be repurposed for AI training and marketing. The privacy page states: "Waymo may share data to improve and analyze its functionality and to tailor products, services, ads, and offers to your interests. You can opt out of sharing your information with third parties, unless it's necessary to the functioning of the service."

Read more of this story at Slashdot.

The United Kingdom has banned "outrageous fake reviews and sneaky hidden fees" to make life easier for online shoppers. From a report: New measures under the Digital Markets, Competition, and Consumer Act 2024 came into force on Sunday that require online platforms to transparently include all mandatory fees within a product's advertised price, including booking or admin charges. The law targets so-called "dripped pricing," in which additional fees -- like platform service charges -- are dripped in during a customer's checkout process to dupe them into paying a higher price than expected. The ban "aims to bring to an end the shock that online shoppers get when they reach the end of their shopping experience only to find a raft of extra fees lumped on top," according to Justin Madders, the UK's Minister for Employment Rights, Competition and Markets.

Read more of this story at Slashdot.

The internet's physical mass remains contested among scientists, with estimates ranging from a strawberry to something almost unimaginably small. In 2006, Harvard physicist Russell Seitz calculated the internet weighed roughly 50 grams based on server energy, a figure that would now equate to potato-weight given internet growth. Christopher White, president of NEC Laboratories America, has dismissed this calculation as "just wrong." White suggests a more accurate method that accounts for the energy needed to encode all internet data in one place, yielding approximately 53 quadrillionths of a gram at room temperature. Alternatively, if the internet's projected 175 zettabytes of data were stored in DNA -- a storage medium scientists are actively exploring -- it would weigh 960,947 grams, equivalent to 10.6 American males. Though scientists debate measurement methods, White asserts the web's true complexity makes it "essentially unknowable."

Read more of this story at Slashdot.

Apple rushed five planeloads of iPhones from India to the U.S. in just three days to beat new tariffs imposed by the Trump administration, Times of India reported Monday, citing sources. The urgent shipments during the final week of March aimed to avoid the 10% reciprocal tariff that took effect on April 5. The stockpiling will allow Apple to maintain current pricing temporarily. "The reserves that arrived at lower duty will temporarily insulate the company from the higher prices that it will need to pay for new shipments," the Indian daily cited a source as saying. The Trump administration also announced a 26% reciprocal tariff to be implemented on April 9, potentially accelerating Apple's manufacturing shift away from China. India offers a significant tariff advantage, with Indian exports facing a 26% tariff to the U.S. compared to 54% on Chinese goods. Further reading: India's Economic Chess Against Twin US Economic Threats.

Read more of this story at Slashdot.

President Donald Trump signaled a potential diplomatic opening amid his aggressive tariff strategy on Monday, threatening China with an additional 50% tariff while simultaneously offering other nations a path to negotiate lower trade barriers. The ultimatum to Beijing demands China withdraw a 34% increase by April 8, 2025, or face supplementary tariffs effective April 9, which would push total levies on Chinese goods to 104% or higher. Trump has already imposed a 20% tariff over fentanyl concerns and a 34% tariff related to trade issues. "Negotiations with other countries, which have requested meetings, will begin taking place immediately," Trump wrote on social media, marking a shift from the administration's previously unyielding stance.

Read more of this story at Slashdot.

A court has blocked a British government attempt to keep secret a legal case over its demand to access Apple user data. From a report: The UK Investigatory Powers Tribunal, a special court that handles cases related to government surveillance, said the authorities' efforts were a "fundamental interference with the principle of open justice" in a ruling issued on Monday. The development comes after it emerged in January that the British government had served Apple with a demand to circumvent encryption that the company uses to secure user data stored in its cloud services. Apple challenged the request, while taking the unprecedented step of removing its advanced data protection feature for its British users. The government had sought to keep details about the demand -- and Apple's challenge of it -- from being publicly disclosed. Apple has regularly clashed with governments over encryption features that can make it difficult for law enforcement to access devices produced by the company. The world's most valuable company last year criticized UK surveillance powers as "unprecedented overreach" by the government.

Read more of this story at Slashdot.

Microsoft's AI chief Mustafa Suleyman says the company has deliberately chosen to build AI models "three or six months behind" cutting-edge developments, citing cost savings and more focused implementation. "It's cheaper to give a specific answer once you've waited for the first three or six months for the frontier to go first. We call that off-frontier," Suleyman told CNBC. "That's actually our strategy, is to really play a very tight second, given the capital-intensiveness of these models." Microsoft owns substantial Nvidia GPU capacity but sees no need to develop "the absolute frontier, the best model in the world first," as it would be "very, very expensive" and create unnecessary duplication, Suleyman said. Despite its $13.75 billion investment in OpenAI, Microsoft added the startup to its list of competitors in July 2024. OpenAI subsequently announced a partnership with Oracle on its $500 billion Stargate project, departing from exclusive reliance on Microsoft's Azure cloud. "Look, it's absolutely mission-critical that long-term, we are able to do AI self-sufficiently at Microsoft," Suleyman said, while stressing the partnership with OpenAI would continue "until 2030 at least."

Read more of this story at Slashdot.

Scientists "demonstrated a promising step toward using a person's own immune cells to fight gastrointestinal cancers" at America's National Institutes of Health (or NIH), reports the Washington Post. But the results were published in Nature Medicine on Tuesday — "the same day the agency was hit with devastating layoffs..." The treatment approach is still early in its development; the personalized immunotherapy regimen shrank tumors in only about a quarter of the patients with colon, rectal and other GI cancers enrolled in a clinical trial. But a researcher who was not involved in the study called the results "remarkable" because they highlight a path to a frustratingly elusive goal in medicine — harnessing a person's own immune defenses to target common solid tumor cancers. Until now, cell-based immunotherapy has worked mainly on blood cancers, such as leukemia, but not the solid cancers that seed tumors in the breast, brain, lungs, pancreas and GI tract... But the progress arrives at a sad time for science — and for patients, said the leader of the work, NIH immunotherapy pioneer Steven Rosenberg. Two patients' treatments using the experimental therapy had to be delayed because NIH's capacity to make personalized cell therapies has been slowed by the firing of highly skilled staff and by purchasing slowdowns. Those occurred even before major layoffs took place Tuesday... The Department of Health and Human Services (HHS) responded to an email asking about clinical trial delays with a statement: "NIH and HHS are complying with President Trump's executive order." It's "a very exciting study," said Patrick Hwu, president of the Moffitt Cancer Center in Tampa. Finding ways to tailor this cell-based immunotherapy approach to common solid tumors that cause the vast majority of cancer deaths has remained a major scientific challenge... Rosenberg and colleagues first tried to create tumor infiltrating lymphocytes [or "TILs"] using the method that worked in melanoma for 18 patients with GI cancers that had spread. It failed completely. In a second iteration, his team sequenced the mutations present in each patient's tumor and used that information to sift out and expand the TILs that could home in on that patient's specific tumor cells. The results were far from a triumph, but provided a clue — this time, three of 39 patients' tumors shrank. In the last stage of the trial, the scientists added a drug called pembrolizumab that takes the brakes off immune cells. This time, eight of the 34 patients responded. "Right now, only a few labs in the country can do what they just did," Hwu said. While Rosenberg is already working "to refine and improve upon the results," he told the Post that two scientists involved in the specialized process of preparing the cells to treat patients were fired in the probationary purge. "We've had to slow down our work and delay the treatment of some patients...." And there's also dramatically fewer people now who can purchase research materials, which the Post says it "making it slower and more difficult to obtain supplies."

Read more of this story at Slashdot.

Brain rot — the inability to think deeply after too much scrolling on a phone — afflicts "plenty of people," writes the New York Times' lead consumer technology writer. [Alternate URL here.] He's suffering from it too — "These days, it's tough to even finish a book." But is the answer just avoiding distractions with a stripped-down $600 phone "that barely does anything"? For a week he tested the Light Phone III... The newest version, which began shipping in March and is set for a broader release in July, can place calls, send texts, take photos, show map directions, play music and podcasts and not do much else. There is no web browser. There is also no app store, meaning there's no Uber to hail a ride, no Slack and no social media. There isn't even email... There were moments I enjoyed it. While waiting for a train, resting at the gym or eating alone, I was not tempted to stare at the phone screen, and I felt more mindful of my surroundings. Phone calls sounded nice and clear. The maps app did a fine job navigating me around town. It reminded me of simpler times when we used phones primarily to converse before putting them away to focus on other tasks. But over the week, the downsides of a dumber phone chipped away at my enjoyment, and overall I felt more stressed and less capable. I suddenly found myself unable to get into a train station, look up the name of a new restaurant or control my garage door. Some of that has less to do with the Light Phone itself, which is a so-so product, and more to do with how society as a whole has become dependent on advanced smartphone features. For example, his old smartphone supported virtual phone-based passes for mass transit and speedy access to his gym. (And his friends made phone of the Light Phone's photos.) But at least never felt tempted to check his email when out to dinner. "While I admire the goal of the Light Phone, my experience demonstrates there's nothing we can realistically do or buy to bring us back to simpler times. So many aspects of our lives, including getting around town, working, paying for things and controlling home appliances, revolve around our highly capable smartphones. "This Light Phone experiment reminded me of glamping: paying a lot to have an artificially crummier experience."

Read more of this story at Slashdot.

"Gen Z is rediscovering Tumblr — a chaotic, cozy corner of the internet untouched by algorithmic gloss and influencer overload..." writes Fast Company, "embracing the platform as a refuge from an internet saturated with influencers and algorithm fatigue." Thanks to Gen Z, the site has found new life. As of 2025, Gen Z makes up 50% of Tumblr's active monthly users and accounts for 60% of new sign-ups, according to data shared with Business Insider's Amanda Hoover, who recently reported on the platform's resurgence. User numbers spiked in January during the near-ban of TikTok and jumped again last year when Brazil temporarily banned X. In response, Tumblr users launched dedicated communities to archive and share their favorite TikToks... To keep up with the momentum, Tumblr introduced Reddit-style Communities in December, letting users connect over shared interests like photography and video games. In January, it debuted Tumblr TV — a TikTok-like feature that serves as both a GIF search engine and a short-form video platform. But perhaps Tumblr's greatest strength is that it isn't TikTok or Facebook. Currently the 10th most popular social platform in the U.S., according to analytics firm Similarweb, Tumblr is dwarfed by giants like Instagram and X. For its users, though, that's part of the appeal. First launched in 2007, Tumblr peaked at over 100 million users in 2014, according to the article. Trends like Occupy Wall Street had been born on Tumblr, notes Business Insider, calling the blogging platform "Gen Z's safe space... as the rest of the social internet has become increasingly commodified, polarized, and dominated by lifestyle influencers." Tumblr was also "one of the most hyped startups in the world before fading into obsolescence — bought by Yahoo for $1.1 billion in 2013... then acquired by Verizon, and later offloaded for fractions of pennies on the dollar in a distressed sale. "That same Tumblr, a relic of many millennials' formative years, has been having a moment among Gen Z..." "Gen Z has this romanticism of the early-2000s internet," says Amanda Brennan, an internet librarian who worked at Tumblr for seven years, leaving her role as head of content in 2021... Part of the reason young people are hanging out on old social platforms is that there's nowhere new to go. The tech industry is evolving at a slower pace than it was in the 2000s, and there's less room for disruption. Big Tech has a stranglehold on how we socialize. That leaves Gen Z to pick up the scraps left by the early online millennials and attempt to craft them into something relevant. They love Pinterest (founded in 2010) and Snapchat (2011), and they're trying out digital point-and-shoot cameras and flip phones for an early-2000s aesthetic — and learning the valuable lesson that sometimes we look better when blurrier. More Gen Zers and millennials are signing up for Yahoo. Napster, surprising many people with its continued existence, just sold for $207 million. The trend is fueled by nostalgia for Y2K aesthetics and a longing for a time when people could make mistakes on the internet and move past them. The pandemic also brought more Gen Z users to Tumblr... And Tumblr still works much like an older internet, where people have more control over what they see and rely less on algorithms. "You curate your own stuff; it takes a little bit of work to put everything in place, but when it's working, you see the content you want to see," Fjodor Everaerts, a 26-year-old in Belgium who has made some 250,000 posts since he joined Tumblr when he was 14... Under Automattic, Tumblr is finally in the home that serves it, [says Ari Levine, the head of brand partnerships at Tumblr]. "We've had ups and downs along the way, but we're in the most interesting position and place that we've been in 18 years," he says... And following media companies (including Business Insider) and social platforms like Reddit, Automattic in 2024 was making a deal with OpenAI and Midjourney to allow the systems to train on Tumblr posts. "The social internet is fractured," the article argues. ("Millennials are running Reddit. Gen Xers and Baby Boomers have a home on Facebook. Bluesky, one of the new X alternatives, has a tangible elder-millennial/Gen X vibe. Gen Zers have created social apps like BeReal and the Myspace-inspired Noplace, but they've so far generated more hype than influence....") But in a world where megaplatforms "flatten our online experiences and reward content that fits a mold," the article suggests, "smaller communities can enrich them."

Read more of this story at Slashdot.

"U.S. stock market futures plunged on Sunday evening," reports Yahoo Finance, "after the new U.S. tariff policy began collecting duties over the weekend..." The EU will vote on $28 billion in retaliatory tariffs Wednesday, Reuters reports. (And those tariffs will be approved unless "a qualified majority of 15 EU members representing 65% of the EU's population oppose it. They would enter force in two stages, a smaller part on April 15 and the rest a month later.") But France's Economy and Finance Minister has an idea: more strictly regulating how data is used by America's Big Tech companies. Politico EU reports/A>: "We may strengthen certain administrative requirements or regulate the use of data," Lombard said in an interview with Le Journal Du Dimanche. He added that another option could be to "tax certain activities," without being more specific. A French government spokesperson already said last week that the EU's retaliation against U.S. tariffs could include "digital services that are currently not taxed." That suggestion was fiercely rejected by Ireland, which hosts the European headquarters of several U.S. Big Tech firms... Technology is seen as a possible area for Europe to retaliate. The European Union has a €157 billion trade surplus in goods, which means it exports more than it imports, but it runs a deficit of €109 billion in services, including digital services. Big Tech giants like Apple, Microsoft, Amazon, Google and Meta dominate many parts of the market in Europe. Amid the market turmoil, what about cryptocurrencies, often seen as a "proxy" for the level of risk felt by investors? In the 10 weeks after October 6, the price of Bitcoin skyrocketed 67% to $106,490 by December 10th. But by January 30th it had started dropping again, and now sits at $77,831 — still up 22% for the last six months, but down nearly 27% over the last 10 weeks. Yet even after all that volatility, Bitcoin suddenly fell again more than 6% on Sunday, reports Reuters, "as markets plunged amid tariff tensions. Ether, the second largest cryptocurrency, fell more than 10% on Sunday."

Read more of this story at Slashdot.

"Three Microsoft CEOs walk into a room..." Satya Nadella posted on X.com, "and are interviewed by Copilot!" As part of Microsoft's 50th anniversary celebration, Microsoft CEO Nadella joined former Microsoft CEOs Bill Gates and Steve Ballmer in a funny two-minute video (also available on YouTube) in which Nadella asks Copilot for an AI-powered roast of each of them. "All right Satya," Copilot answers. "Let's spice it up..." Copilot: Steve, we'll start with you. Your enthusiasm is legendary. But do you ever worry that your energy might short-circuit the AI? I mean, even robots need a coffee break after your pep talks. Steve Ballmer: Come on dude! If you can't handle me, you can't handle a huge percentage of the world's population! We're counting on you! Copilot: Ha ha, fair point Steve. Now Bill, you've got that signature thoughtful gaze. But do you ever think the AI might feel intimidated by your intense thinking face? I mean, it's like it's waiting for a blue screen moment. Bill Gates: I hope so. I mean, it's all I've got left as the AIs get so damn intelligent. It's just that gaze and my willingness to criticize that differentiates me. Copilot: And it's a formidable gaze indeed, Bill. Steve Ballmer: Copilot, would you ever be willing to criticize him? Copilot: Absolutely. Criticism is where growth happens. Now Satya, AI seems to be your best buddy — but ever worry that your deep passion for AI could one day have it running the show, leaving you to just enjoy the ride? Satya Nadella: Well, the day AI can play like the best cricket player that I enjoy, that's the day it can run the show, as far as I'm concerned. Copilot: Touche, Satya. Let's see if it can hit a century in cricket and then we'll talk. This has been a blast, gentlemen. Here's to another 50 years of innovation and adventure. Cheers. Ballmer, Nadella, and Gates: Cheers. Bill Gates: Whatever that means to an AI. Does it drink?

Read more of this story at Slashdot.

Nuclear fusion — which releases four times the energy of fission — could theoretically happen sooner in space than on earth, reports CNN. "And it could help spacecraft achieve speeds of up to 500,000 miles (805,000 kilometers) per hour — more than the fastest object ever built..." With funding from the UK Space Agency, British startup Pulsar Fusion has unveiled Sunbird, a space rocket concept designed to meet spacecraft in orbit, attach to them, and carry them to their destination at breakneck speed using nuclear fusion... For now, Sunbird is in the very early stages of construction and it has exceptional engineering challenges to overcome, but Pulsar says it hopes to achieve fusion in orbit for the first time in 2027. [Pulsar's founder/CEO says the first functional Sunbird would be ready four to five years later.] If the rocket ever becomes operational, it could one day cut the journey time of a potential mission to Mars in half. CNN says the proposed Sunbird process would use helium-3 — which may be abundant on the Moon — to generate protons which "can be used as a 'nuclear exhaust' to provide propulsion". (And without generating any dangerous radioactive material.) "It's very unnatural to do fusion on Earth," says Richard Dinan, founder and CEO of Pulsar. "Fusion doesn't want to work in an atmosphere. Space is a far more logical, sensible place to do fusion, because that's where it wants to happen anyway...." Sunbirds would operate similarly to city bikes at docking stations, according to Dinan: "We launch them into space, and we would have a charging station where they could sit and then meet your ship," he says. "You turn off your inefficient combustion engines, and use nuclear fusion for the greater part of your journey. Ideally, you'd have a station somewhere near Mars, and you'd have a station on low Earth orbit, and the (Sunbirds) would just go back and forth...." Initially, the Sunbirds will be offered for shuttling satellites in orbit, but their true potential would come into play with interplanetary missions. The company illustrates a few examples of the missions that Sunbird could unlock, such as delivering up to 2,000 kilograms (4,400 pounds) of cargo to Mars in under six months, deploying probes to Jupiter or Saturn in two to four years (NASA's Europa Clipper, launched in 2024 towards one of Jupiter's moons, will arrive after 5.5 years), and an asteroid mining mission that would complete a round trip to a near-Earth asteroid in one to two years instead of three. Other companies are working on nuclear fusion engines for space propulsion, including Pasadena-based Helicity Space, which received investment from aerospace giant Lockheed Martin in 2024. San Diego-based General Atomics and NASA are working on another type of nuclear reactor — based on fission rather than fusion — which they plan to test in space in 2027.

Read more of this story at Slashdot.

It was already the best-selling videogame of all time, notes the Hollywood Reporter. And A Minecraft Movie just had the biggest opening ever for a video game movie adaptation. WIth a production budget of $150 million, it earned in $157 million in just its first weekend in the U.S., with a worldwide total of $301 million. A Warner Bros. executive called the movie "lightning in a bottle," while the head of co-producer Legendary Pictures acknowledged the game is a global phenomon, according to the article. (About the movie's performance, the executive "said the opening is a both a reflection of the mandate to celebrate the world of Minecraft in a joyful way, and the singular experience that only theatrical can offer." But an unfinished version leaked online before the movie was even released, reports Variety Screenshots and footage from the fantasy adventure were being shared widely on social media platforms this week, and were also available on file sharing sites. The images and scenes have uncompleted visual effects. Most of the footage was quickly taken down by the rights holders. Although pirated footage is a common problem for major film releases, it's rare to have a working print leak online in this way, raising questions about how such an early version of the movie was accessed, stolen and then shared.

Read more of this story at Slashdot.

theodp writes: America's National Football League announced that beginning with the 2025 season, Sony's Hawk-Eye virtual measurement technology will assess and identify first downs after a ball spot. Sony's Hawk-Eye virtual measurement technology, which consists of six 8K cameras for optical tracking of the position of the ball, is operated from the NFL's "Art McNally GameDay Central Officiating Center" in New York and is integrated with the League's existing replay system. It will serve as an efficient alternative to the process of having a three-person chain crew walk chains onto the field and manually measure whether 10 yards have been met after the official has spotted the ball. However, the chain crew will remain on the field in a secondary capacity. The NFL's executive VP of football operations says their move brings "world-class on field officiating with state-of-the-art technology to advance football excellence." (The NFL's announcement notes the whole process takes about 30 seconds, "saving up to 40 seconds from a measurement with the chains.") The move comes a full seven years after Apple introduced its iPhone Measure app...

Read more of this story at Slashdot.

It's "a milestone for Meta AI and for open source," Mark Zuckerberg said this weekend. "For the first time, the best small, mid-size, and potentially soon frontier [large-language] models will be open source." Zuckerberg anounced four new Llama LLMs in a video posted on Instagram and Facebook — two dropping this weekend, with another two on the way. "Our goal is to build the world's leading AI, open source it, and make it universally accessible so that everyone in the world benefits." Zuckerberg's announcement: I've said for a while that I think open source AI is going to become the leading models. And with Llama 4 this is starting to happen. - The first model is Llama 4 Scout. It is extremely fast, natively multi-modal. It has an industry-leading "nearly infinite" 10M-token context length, and is designed to run on a single GPU. [Meta's blog post says it fits on an NVIDIA H100]. It is 17 billion parameters by 16 experts, and it is by far the highest performing small model in its class. - The second model is Llama 4 Maverick — the workhorse. It beats GPT-4o and Gemini Flash 2 on all benchmarks. It is smaller and more efficient than DeepSeek v3, but it is still comparable on text, plus it is natively multi-modal. This one is 17B parameters x 128 experts, and it is designed to run on a single host for easy inference. This thing is a beast. Zuck promised more news next month on "Llama 4 Reasoning" — but the fourth model will be called Llama 4 Behemoth. "This thing is massive. More than 2 trillion parameters." (A blog post from Meta AI says it also has a 288 billion active parameter model, outperforms GPT-4.5, Claude Sonnet 3.7, and Gemini 2.0 Pro on STEM benchmarks, and will "serve as a teacher for our new models.") "I'm not aware of anyone training a larger model out there," Zuckberg says in his video, calling Behemoth "already the highest performing base model in the world, and it is not even done training yet." "If you want to try Llama 4, you can use Meta AI in WhatsApp, Messenger, or Instagram Direct," Zuckberg said in his video, "or you can go to our web site at meta.ai." The Scout and Maverick models can be downloaded from llama.com and Hugging Face. "We continue to believe that openness drives innovation," Meta AI says in their blog post, "and is good for developers, good for Meta, and good for the world." Their blog post declares it's "The beginning of a new era of natively multimodal AI innovation," calling Scout and Maverick "the best choices for adding next-generation intelligence." This is just the beginning for the Llama 4 collection. We believe that the most intelligent systems need to be capable of taking generalized actions, conversing naturally with humans, and working through challenging problems they haven't seen before. Giving Llama superpowers in these areas will lead to better products for people on our platforms and more opportunities for developers to innovate on the next big consumer and business use cases. We're continuing to research and prototype both models and products, and we'll share more about our vision at LlamaCon on April 29... We also can't wait to see the incredible new experiences the community builds with our new Llama 4 models. "The impressive part about Llama 4 Maverick is that with just 17B active parameters, it has scored an ELO score of 1,417 on the LMArena leaderboard," notes the tech news site Beebom. "This puts the Maverick model in the second spot, just below Gemini 2.5 Pro, and above Grok 3, GPT-4o, GPT-4.5, and more. "It also achieves comparable results when compared to the latest DeepSeek V3 model on reasoning and coding tasks, and surprisingly, with just half the active parameters."

Read more of this story at Slashdot.

It was long-time Slashdot reader uninet who argued "Apple Needs a Snow Sequoia." (That is, Apple needs an upgrade to MacOS Sequoia that's like it's earlier "Snow Leopard" upgrade to "Leopard" OS — an upgrade that's "all about how little it added and how much it took away".) "My recent column on Apple's declining software quality hit a nerve..." he writes in a follow-up. "So why do any of us put up with software that grows increasingly buggy?" "One word: hardware. And that's where I'd love to see someone help Linux take the next step." Apple knows how to turn out very good quality pieces of hardware and, for many purposes, stands alone. That's been largely true for the last couple of decades. The half-decade of Apple Silicon has cemented this position. At any price point Apple contends, Macs, iPads and iPhones are either without peers or at the top of the market in build quality and processing power... [I]f only there were hardware that was as good and worked together as well as Apple's, jumping ship to Linux would be awfully attractive at this juncture... For Apple aficionados troubled by the state of MacOS, the modern GNOME desktop on Linux beckons as a more faithful implementation of the ideals of MacOS than current MacOS does. GNOME is painstakingly consistent across its different apps and exudes the minimalist philosophy with which Apple's hardware shines... Now is a perfect moment for a modern Linux push to take that wind back. What it needs, though, is to solve its remaining weakness on the hardware side. One of the giants of electronics manufacturing, tired of being stuck between the Microsoft and Apple ecosystems, would only need to decide to commit the resources necessary to solve the hardware puzzle... ChromeOS has grown to the extent it does because there is hardware designed for it. Take that and carry it further by making it good hardware utilizing the best Linux software and you'd have something disruptive... Initially, the hardware could be "good enough" for the software, much as Apple's software today is merely "good enough" for the hardware. Iterating from there could lead to a genuine third way of computing. They titled their piece, "I Want a Better Mac, so I'm Cheering for a Better Linux." (Wondering if Dell or Sony could be the one to supply that good hardware...) "I say this not as someone who thinks Linux will ever dominate the personal computing world, but as someone who wants to see a spark of creativity and push beyond mediocrity in it again. "Apple needs a real competitor, one alternatives such as GNOME on Linux could actually be, if only the hardware rose to the occasion."

Read more of this story at Slashdot.

Tinder "is experimenting with a chatbot that claims to help users improve their flirting skills," notes Washington Post internet-culture reporter Tatum Hunter. The chatbot is available only to users in the United States on iPhones for a limited time, and powered by OpenAI's GPT-4o each character "kicks off an improvised conversation, and the user responds out loud with something flirty..." "Three of them dumped me." You can win points for banter the app deems "charming" or "playful." You lose points if your back-and-forth seems "cheeky" or "quirky"... It asked me to talk out loud into my phone and win the romantic interest of various AI characters. The first scenario involved a financial analyst named Charles, whom I've supposedly run into at the Tokyo airport after accidentally swapping our luggage. I tried my best to be polite to the finance guy who stole my suitcase, asking questions about his travel and agreeing to go to coffee. But the game had some critical feedback: I should try to connect more emotionally using humor or stories from my life. My next go had me at a Dallas wedding trying to flirt with Andrew, a data analyst who had supposedly stumbled into the venue, underdressed, because he'd been looking for a quiet spot to ... analyze data. This time I kept things playful, poking fun at Andrew for crashing a wedding. Andrew didn't like that. I'd "opted to disengage" by teasing this person instead of helping him blend in at the wedding, the app said. A failure on my part, apparently — and also a reminder why generative AI doesn't belong everywhere... Going in, I was worried Tinder's AI characters would outperform the people I've met on dating apps and I'd fall down a rabbit hole of robot love. Instead, they behaved in a way typical for chatbots: Drifting toward biased norms and failing to capture the complexity of human emotions and interactions. The "Game Game" seemed to replicate the worst parts of flirting — the confusion, the unclear expectations, the uncomfortable power dynamics — without the good parts, like the spark of curiosity about another person. Tinder released the feature on April Fools' Day, likely as a bid for impressions and traffic. But its limitations overshadowed its novelty... Hillary Paine, Tinder's vice president of product, growth and revenue, said in an email that AI will play a "big role in the future of dating and Tinder's evolution." She said the game is meant to be silly and that the company "leaned into the campiness." Gen Z is a socially anxious generation, Paine said, and this age group is willing to endure a little cringe if it leads to a "real connection." The article suggests it's another example of companies "eager to incorporate this newish technology, often without considering whether it adds any value for users." But "As apps like Tinder and Bumble lose users amid 'dating app burnout,' the companies are turning to AI to win new growth." (The dating app Rizz "uses AI to autosuggest good lines to use," while Teaser "spins up a chatbot that's based on your personality, meant to talk and behave like you would during a flirty chat," and people "are forming relationships with AI companion bots by the millions.") And the companion-bot company Replika "boasts more than 30 million users..."

Read more of this story at Slashdot.

This October will see the release of a film that's nearly 43 years in the making, reports Ars Technica: It's difficult to underestimate the massive influence that Disney's 1982 cult science fiction film, TRON, had on both the film industry — thanks to combining live action with what were then groundbreaking visual effects rife with computer-generated imagery — and on nerd culture at large. Over the ensuing decades there has been one sequel, an animated TV series, a comic book miniseries, video games, and theme park attractions, all modeled on director Steve Lisberg's original fictional world. Now we're getting a third installment in the film franchise: TRON: Ares, directed by Joachim Rønning (Pirates of the Caribbean: Dead Men Tell No Tales, Maleficent: Mistress of Evil), that serves as a standalone sequel to 2010's TRON: Legacy. Disney just released the first trailer and poster art, and while the footage is short on plot, it's got the show-stopping visuals we've come to expect from all things TRON. The film's director says it "builds upon the legacy of cutting-edge design, technology and storytelling, according to an official statement from Disney. And here's how they describe the plot. "TRON: Ares follows a highly sophisticated Program, Ares, who is sent from the digital world into the real world on a dangerous mission, marking humankind's first encounter with A.I. beings." Share your thoughts in the comments. (Anyone remember playing the Tron videogame?) The first episode of 2012's animated Tron: Uprising is available on the Disney XD YouTube channel...

Read more of this story at Slashdot.

U.K. postmasters were mistakenly sent to prison due to a bug in their "Horizon" accounting software — as first reported by Computer Weekly back in 2009. Nearly 16 years later, the same site reports that now the Scottish Criminal Cases Review Commission "is attempting to contact any former subpostmasters that could have been prosecuted for unexplained losses on the Post Office's pre-Horizon Capture software. "There are former subpostmasters that, like Horizon users, could have been convicted of crimes based on data from these systems..." Since the Post Office Horizon scandal hit the mainstream in January 2024 — revealing to a wide audience the suffering experienced by subpostmasters who were blamed for errors in the Horizon accounting system — users of Post Office software that predated Horizon have come forward... to tell their stories, which echoed those of victims of the Horizon scandal. The Criminal Cases Review Commission for England and Wales is now reviewing 21 cases of potential wrongful conviction... where the Capture IT system could be a factor... The SCCRC is now calling on people that might have been convicted based on Capture accounts to come forward. "The commission encourages anyone who believes that their criminal conviction, or that of a relative, might have been affected by the Capture system to make contact with it," it said. The statutory body is also investigating a third Post Office system, known as Ecco+, which was also error-prone... A total of 64 former subpostmasters in Scotland have now had their convictions overturned through the legislation brought through Scottish Parliament. So far, 97 convicted subpostmasters have come forward, and 86 have been assessed, out of which the 64 have been overturned. However, 22 have been rejected and another 11 are still to be assessed. An independent group, fronted by a former Scottish subpostmaster, is also calling on users of any of the Post Office systems to come forward to tell their stories, and for support in seeking justice and redress.

Read more of this story at Slashdot.

The Starliner spacecraft lost four thrusters while approaching the International Space Station last summer. NASA astronaut, Butch Wilmore took manual control, remembers Ars Technica, "But as Starliner's thrusters failed, Wilmore lost the ability to move the spacecraft in the direction he wanted to go..." Starliner had flown to within a stone's throw of the space station, a safe harbor, if only they could reach it. But already, the failure of so many thrusters violated the mission's flight rules. In such an instance, they were supposed to turn around and come back to Earth. Approaching the station was deemed too risky for Wilmore and Williams, aboard Starliner, as well as for the astronauts on the $100 billion space station. But what if it was not safe to come home, either? "I don't know that we can come back to Earth at that point," Wilmore said in an interview. "I don't know if we can. And matter of fact, I'm thinking we probably can't." After a half-hour exclusive interview, Ars Technica's senior space editor Eric Berger says he'd heard "a hell of a story." After Starliner lost four of its 28 reaction control system thrusters, Van Cise and this team in Houston decided the best chance for success was resetting the failed thrusters. This is, effectively, a fancy way of turning off your computer and rebooting it to try to fix the problem. But it meant Wilmore had to go hands-off from Starliner's controls. Imagine that. You're drifting away from the space station, trying to maintain your position. The station is your only real lifeline because if you lose the ability to dock, the chance of coming back in one piece is quite low. And now you're being told to take your hands off the controls... Two of the four thrusters came back online. Wilmore: "...But then we lose a fifth jet. What if we'd have lost that fifth jet while those other four were still down? I have no idea what would've happened. I attribute to the providence of the Lord getting those two jets back before that fifth one failed... Berger: Mission Control decided that it wanted to try to recover the failed thrusters again. After Wilmore took his hands off the controls, this process recovered all but one of them. At that point, the vehicle could be flown autonomously, as it was intended to be. "Wilmore added that he felt pretty confident, in the aftermath of docking to the space station, that Starliner probably would not be their ride home," according to the article. And Williams says it was the right decision. Publicly, NASA and Boeing expressed confidence in Starliner's safe return with crew. But Williams and Wilmore, who had just made that harrowing ride, felt differently.

Read more of this story at Slashdot.

Microsoft has created a real-time AI-generated rendition of Quake II gameplay (playable on the web). Friday Xbox's general manager of gaming AI posted the startling link to "an AI-generated gaming experience" at Copilot.Microsoft.com "Move, shoot, explore — and every frame is created on the fly by an AI world model, responding to player inputs in real-time. Try it here." They started with their "Muse" videogame world models, adding "a real-time playable extension" that players can interact with through keyboard/controller actions, "essentially allowing you to play inside the model," according to a Microsoft blog post. A concerted effort by the team resulted in both planning out what data to collect (what game, how should the testers play said game, what kind of behaviours might we need to train a world model, etc), and the actual collection, preparation, and cleaning of the data required for model training. Much to our initial delight we were able to play inside the world that the model was simulating. We could wander around, move the camera, jump, crouch, shoot, and even blow-up barrels similar to the original game. Additionally, since it features in our data, we can also discover some of the secrets hidden in this level of Quake II. We can also insert images into the models' context and have those modifications persist in the scene... We do not intend for this to fully replicate the actual experience of playing the original Quake II game. This is intended to be a research exploration of what we are able to build using current ML approaches. Think of this as playing the model as opposed to playing the game... The interactions with enemy characters is a big area for improvement in our current WHAMM model. Often, they will appear fuzzy in the images and combat with them (damage being dealt to both the enemy/player) can be incorrect. They warn that the model "can and will forget about objects that go out of view" for longer than 0.9 seconds. "This can also be a source of fun, whereby you can defeat or spawn enemies by looking at the floor for a second and then looking back up. Or it can let you teleport around the map by looking up at the sky and then back down. These are some examples of playing the model." This generative AI model was trained on Quake II "with just over a week of data," reports Tom's Hardware — a dramatic reduction from the seven years required for the original model launched in February. Some context from The Verge: "You could imagine a world where from gameplay data and video that a model could learn old games and really make them portable to any platform where these models could run," said Microsoft Gaming CEO Phil Spencer in February. "We've talked about game preservation as an activity for us, and these models and their ability to learn completely how a game plays without the necessity of the original engine running on the original hardware opens up a ton of opportunity." "Is porting a game like Gameday 98 more feasible through AI or a small team?" asks the blog Windows Central. "What costs less or even takes less time? These are questions we'll be asking and answering over the coming decade as AI continues to grow. We're in year two of the AI boom; I'm terrified of what we'll see in year 10." "It's clear that Microsoft is now training Muse on more games than just Bleeding Edge," notes The Verge, "and it's likely we'll see more short interactive AI game experiences in Copilot Labs soon." Microsoft is also working on turning Copilot into a coach for games, allowing the AI assistant to see what you're playing and help with tips and guides. Part of that experience will be available to Windows Insiders through Copilot Vision soon.

Read more of this story at Slashdot.

Berkeley, California is "the latest city to try to block landlords from using algorithms when deciding rents," reports the Associated Press (noting that officials in many cities claim the practice is driving up the price of housing). But then real estate software company RealPage filed a federal lawsuit against Berkeley on Wednesday: Texas-based RealPage said Berkeley's ordinance, which goes into effect this month, violates the company's free speech rights and is the result of an "intentional campaign of misinformation and often-repeated false claims" about its products. The U.S. Department of Justice sued Realpage in August under former President Joe Biden, saying its algorithm combines confidential information from each real estate management company in ways that enable landlords to align prices and avoid competition that would otherwise push down rents. That amounts to cartel-like illegal price collusion, prosecutors said. RealPage's clients include huge landlords who collectively oversee millions of units across the U.S. In the lawsuit, the Department of Justice pointed to RealPage executives' own words about how their product maximizes prices for landlords. One executive said, "There is greater good in everybody succeeding versus essentially trying to compete against one another in a way that actually keeps the entire industry down." San Francisco, Philadelphia and Minneapolis have since passed ordinances restricting landlords from using rental algorithms. The Department of Justice case remains ongoing, as do lawsuits against RealPage brought by tenants and the attorneys general of Arizona and Washington, D.C... [On a conference call, RealPage attorney Stephen Weissman told reporters] RealPage officials were never given an opportunity to present their arguments to the Berkeley City Council before the ordinance was passed and said the company is considering legal action against other cities that have passed similar policies, including San Francisco. RealPage blames high rents not on the software they make, but on a lack of housing supply...

Read more of this story at Slashdot.

Over on Reddit's "selfhosted" subreddit for alternatives to popular services, long-time Slashdot reader Zoup described a pain point: - Landlock is a Linux Security Module (LSM) that lets unprivileged processes restrict themselves. - It's been in the kernel since 5.13, but the API is awkward to use directly. - It always annoyed the hell out of me to run random binaries from the internet without any real control over what they can access. So they've rolled their own solution, according to Thursday's submission to Slashdot: I just released Landrun, a Go-based CLI tool that wraps Linux Landlock (5.13+) to sandbox any process without root, containers, or seccomp. Think firejail, but minimal and kernel-native. Supports fine-grained file access (ro/rw/exec) and TCP port restrictions (6.7+). No daemons, no YAML, just flags. Example (where --rox allows read-only access with execution to specified path): # landrun --rox /usr touch /tmp/filetouch: cannot touch '/tmp/file': Permission denied# landrun --rox /usr --rw /tmp touch /tmp/file# It's MIT-licensed, easy to audit, and now supports systemd services.

Read more of this story at Slashdot.

"The third James Bond novel was published on this day in 1955," writes long-time Slashdot reader sandbagger. Film buff Christian Petrozza shares some history: In 1979, the market was hot amid the studios to make the next big space opera. Star Wars blew up the box office in 1977 with Alien soon following and while audiences eagerly awaited the next installment of George Lucas' The Empire Strikes Back, Hollywood was buzzing with spacesuits, lasers, and ships that cruised the stars. Politically, the Cold War between the United States and Russia was still a hot topic, with the James Bond franchise fanning the flames in the media entertainment sector. Moon missions had just finished their run in the early 70s and the space race was still generationally fresh. With all this in mind, as well as the successful run of Roger Moore's fun and campy Bond, the time seemed ripe to boldly take the globe-trotting Bond where no spy has gone before. Thus, 1979's Moonraker blasted off to theatres, full of chrome space-suits, laser guns, and jetpacks, the franchise went full-boar science fiction to keep up with the Joneses of current Hollywood's hottest genre. The film was a commercial smash hit, grossing 210 million worldwide. Despite some mixed reviews from critics, audiences seemed jazzed about seeing James Bond in space. When it comes to adaptations of the novella that Ian Flemming wrote of the same name, Moonraker couldn't be farther from its source material, and may as well be renamed completely to avoid any association... Ian Flemming's original Moonraker was more of a post-war commentary on the domestic fears of modern weapons being turned on Europe by enemies who were hired for science by newer foes. With Nazi scientists being hired by both the U.S. and Russia to build weapons of mass destruction after World War II, this was less of a Sci-Fi and much more of a cautionary tale. They argue that filming a new version of Moonraker "to find a happy medium between the glamor and the grit of the James Bond franchise..."

Read more of this story at Slashdot.

This week NASA "issued a solicitation for the next two private astronaut missions to the International Space Station," reports Space News. Scheduled after May of 2026 and then mid-2027, "These will be the fifth and sixth such missions to the ISS, part of a broader low Earth orbit commercialization effort by NASA with the ultimate goal of replacing the International Space Station with one or more commercial stations." NASA's Space Station program manager calls the missions "a key part" of helping industry partners "gain the experience needed to train and manage crews, conduct research, and develop future destinations." In short, they see the missions "providing companies with hands-on opportunities to refine their capabilities and build partnerships that will shape the future of low Earth orbit." [NASA's call for proposals] offers an opportunity to have future missions commanded by someone other than a former NASA astronaut. While companies must propose a commander who meets current requirements, it can also propose an alternate commander who is a former astronaut from the Canadian Space Agency, European Space Agency or Japan Aerospace Exploration Agency with similar ISS experience requirements... ["Broadening of this requirement is not guaranteed," NASA warns.] That could allow some former astronauts already working with commercial spaceflight companies an opportunity to command private astronaut missions. Axiom Space, for example, announced in July 2024 that former ESA astronaut Tim Peake had joined its astronaut team. That came after Axiom and the U.K. Space Agency signed a memorandum of understanding in October 2023 to study the feasibility of a private astronaut mission crewed exclusively by U.K. astronauts. So far Axiom Space has been awarded all four private astronaut missions, according to the article, "flying one mission each in 2022, 2023 and 2024. Its next mission, Ax-4, is scheduled for no earlier than May." But "While Axiom has little or no competition for previous PAM awards, it will likely face stiffer competition this time. Vast, a company also planning to develop commercial space stations, has previously stated its intent to submit proposals..."

Read more of this story at Slashdot.

Slashdot reader zlives shared this report from BleepingComputer: Microsoft used its AI-powered Security Copilot to discover 20 previously unknown vulnerabilities in the GRUB2, U-Boot, and Barebox open-source bootloaders. GRUB2 (GRand Unified Bootloader) is the default boot loader for most Linux distributions, including Ubuntu, while U-Boot and Barebox are commonly used in embedded and IoT devices. Microsoft discovered eleven vulnerabilities in GRUB2, including integer and buffer overflows in filesystem parsers, command flaws, and a side-channel in cryptographic comparison. Additionally, 9 buffer overflows in parsing SquashFS, EXT4, CramFS, JFFS2, and symlinks were discovered in U-Boot and Barebox, which require physical access to exploit. The newly discovered flaws impact devices relying on UEFI Secure Boot, and if the right conditions are met, attackers can bypass security protections to execute arbitrary code on the device. While exploiting these flaws would likely need local access to devices, previous bootkit attacks like BlackLotus achieved this through malware infections. Miccrosoft titled its blog post "Analyzing open-source bootloaders: Finding vulnerabilities faster with AI." (And they do note that Micxrosoft disclosed the discovered vulnerabilities to the GRUB2, U-boot, and Barebox maintainers and "worked with the GRUB2 maintainers to contribute fixes... GRUB2 maintainers released security updates on February 18, 2025, and both the U-boot and Barebox maintainers released updates on February 19, 2025.") They add that performing their initial research, using Security Copilot "saved our team approximately a week's worth of time," Microsoft writes, "that would have otherwise been spent manually reviewing the content." Through a series of prompts, we identified and refined security issues, ultimately uncovering an exploitable integer overflow vulnerability. Copilot also assisted in finding similar patterns in other files, ensuring comprehensive coverage and validation of our findings... As AI continues to emerge as a key tool in the cybersecurity community, Microsoft emphasizes the importance of vendors and researchers maintaining their focus on information sharing. This approach ensures that AI's advantages in rapid vulnerability discovery, remediation, and accelerated security operations can effectively counter malicious actors' attempts to use AI to scale common attack tactics, techniques, and procedures (TTPs). This week Google also announced Sec-Gemini v1, "a new experimental AI model focused on advancing cybersecurity AI frontiers."

Read more of this story at Slashdot.

The advent of LLMs and machine learning-based applications "opened the door to a new wave of security threats," argues Google's security blog. (Including model and data poisoning, prompt injection, prompt leaking and prompt evasion.) So as part of the Linux Foundation's nonprofit Open Source Security Foundation, and in partnership with NVIDIA and HiddenLayer, Google's Open Source Security Team on Friday announced the first stable model-signing library (hosted at PyPI.org), with digital signatures letting users verify that the model used by their application "is exactly the model that was created by the developers," according to a post on Google's security blog. [S]ince models are an uninspectable collection of weights (sometimes also with arbitrary code), an attacker can tamper with them and achieve significant impact to those using the models. Users, developers, and practitioners need to examine an important question during their risk assessment process: "can I trust this model?" Since its launch, Google's Secure AI Framework (SAIF) has created guidance and technical solutions for creating AI applications that users can trust. A first step in achieving trust in the model is to permit users to verify its integrity and provenance, to prevent tampering across all processes from training to usage, via cryptographic signing... [T]he signature would have to be verified when the model gets uploaded to a model hub, when the model gets selected to be deployed into an application (embedded or via remote APIs) and when the model is used as an intermediary during another training run. Assuming the training infrastructure is trustworthy and not compromised, this approach guarantees that each model user can trust the model... The average developer, however, would not want to manage keys and rotate them on compromise. These challenges are addressed by using Sigstore, a collection of tools and services that make code signing secure and easy. By binding an OpenID Connect token to a workload or developer identity, Sigstore alleviates the need to manage or rotate long-lived secrets. Furthermore, signing is made transparent so signatures over malicious artifacts could be audited in a public transparency log, by anyone. This ensures that split-view attacks are not possible, so any user would get the exact same model. These features are why we recommend Sigstore's signing mechanism as the default approach for signing ML models. Today the OSS community is releasing the v1.0 stable version of our model signing library as a Python package supporting Sigstore and traditional signing methods. This model signing library is specialized to handle the sheer scale of ML models (which are usually much larger than traditional software components), and handles signing models represented as a directory tree. The package provides CLI utilities so that users can sign and verify model signatures for individual models. The package can also be used as a library which we plan to incorporate directly into model hub upload flows as well as into ML frameworks. "We can view model signing as establishing the foundation of trust in the ML ecosystem..." the post concludes (adding "We envision extending this approach to also include datasets and other ML-related artifacts.") Then, we plan to build on top of signatures, towards fully tamper-proof metadata records, that can be read by both humans and machines. This has the potential to automate a significant fraction of the work needed to perform incident response in case of a compromise in the ML world... To shape the future of building tamper-proof ML, join the Coalition for Secure AI, where we are planning to work on building the entire trust ecosystem together with the open source community. In collaboration with multiple industry partners, we are starting up a special interest group under CoSAI for defining the future of ML signing and including tamper-proof ML metadata, such as model cards and evaluation results.

Read more of this story at Slashdot.

Back in 2023 Python's infrastructure director called it "the first step in our plan to build financial support and long-term sustainability of PyPI" while giving users "one of our most requested features: organization accounts." (That is, "self-managed teams with their own exclusive branded web addresses" to make their massive Python Package Index repository "easier to use for large community projects, organizations, or companies who manage multiple sub-teams and multiple packages.") Nearly two years later, they've announced that they're "making progress" on its rollout... Over the last month, we have taken some more baby steps to onboard new Organizations, welcoming 61 new Community Organizations and our first 18 Company Organizations. We're still working to improve the review and approval process and hope to improve our processing speed over time. To date, we have 3,562 Community and 6,424 Company Organization requests to process in our backlog. They've also onboarded a PyPI Support Specialist to provide "critical bandwidth to review the backlog of requests" and "free up staff engineering time to develop features to assist in that review." (And "we were finally able to finalize our Terms of Service document for PyPI," build the tooling necessary to notify users, and initiate the Terms of Service rollout. [Since launching 20 years ago PyPi's terms of service have only been updated twice.] In other news the security developer-in-residence at the Python Software Foundation has been continuing work on a Software Bill-of-Materials (SBOM) as described in Python Enhancement Proposal #770. The feature "would designate a specific directory inside of Python package metadata (".dist-info/sboms") as a directory where build backends and other tools can store SBOM documents that describe components within the package beyond the top-level component." The goal of this project is to make bundled dependencies measurable by software analysis tools like vulnerability scanning, license compliance, and static analysis tools. Bundled dependencies are common for scientific computing and AI packages, but also generally in packages that use multiple programming languages like C, C++, Rust, and JavaScript. The PEP has been moved to Provisional Status, meaning the PEP sponsor is doing a final review before tools can begin implementing the PEP ahead of its final acceptance into changing Python packaging standards. Seth has begun implementing code that tools can use when adopting the PEP, such as a project which abstracts different Linux system package managers functionality to reverse a file path into the providing package metadata. Security developer-in-residence Seth Larson will be speaking about this project at PyCon US 2025 in Pittsburgh, PA in a talk titled "Phantom Dependencies: is your requirements.txt haunted?" Meanwhile InfoWorld reports that newly approved Python Enhancement Proposal 751 will also give Python a standard lock file format.

Read more of this story at Slashdot.

Wikipedia remembers Dave Täht as "an American network engineer, musician, lecturer, asteroid exploration advocate, and Internet activist. He was the chief executive officer of TekLibre." But on X.com Eric S. Raymond called him "one of the unsung heroes of the Internet, and a close friend of mine who I will miss very badly." Dave, known on X as @mtaht because his birth name was Michael, was a true hacker of the old school who touched the lives of everybody using X. His work on mitigating bufferbloat improved practical TCP/IP performance tremendously, especially around video streaming and other applications requiring low latency. Without him, Netflix and similar services might still be plagued by glitches and stutters. Also on X, legendary game developer John Carmack remembered that Täht "did a great service for online gamers with his long campaign against bufferbloat in routers and access points. There is a very good chance your packets flow through some code he wrote." (Carmack also says he and Täht "corresponded for years".) Long-time Slashdot reader TheBracket remembers him as "the driving force behind ">the Bufferbloat project and a contributor to FQ-CoDel, and CAKE in the Linux kernel." Dave spent years doing battle with Internet latency and bufferbloat, contributing to countless projects. In recent years, he's been working with Robert, Frank and myself at LibreQoS to provide CAKE at the ISP level, helping Starlink with their latency and bufferbloat, and assisting the OpenWrt project. Eric Raymond remembered first meeting Täht in 2001 "near the peak of my Mr. Famous Guy years. Once, sometimes twice a year he'd come visit, carrying his guitar, and crash out in my basement for a week or so hacking on stuff. A lot of the central work on bufferbloat got done while I was figuratively looking over his shoulder..." Raymond said Täht "lived for the work he did" and "bore deteriorating health stoically. While I know him he went blind in one eye and was diagnosed with multiple sclerosis." He barely let it slow him down. Despite constantly griping in later years about being burned out on programming, he kept not only doing excellent work but bringing good work out of others, assembling teams of amazing collaborators to tackle problems lesser men would have considered intractable... Dave should have been famous, and he should have been rich. If he had a cent for every dollar of value he generated in the world he probably could have bought the entire country of Nicaragua and had enough left over to finance a space program. He joked about wanting to do the latter, and I don't think he was actually joking... In the invisible college of people who made the Internet run, he was among the best of us. He said I inspired him, but I often thought he was a better and more selfless man than me. Ave atque vale, Dave. Weeks before his death Täht was still active on X.com, retweeting LWN's article about "The AI scraperbot scourge", an announcement from Texas Instruments, and even a Slashdot headline. Täht was also Slashdot reader #603,670, submitting stories about network latency, leaving comments about AI, and making announcements about the Bufferbloat project.

Read more of this story at Slashdot.

Is OpenAI's ChatGPT violating copyrights? The New York Times sued OpenAI in December 2023. But Ars Technica summarizes OpenAI's response. The New York Times (or NYT) "should have known that ChatGPT was being trained on its articles... partly because of the newspaper's own reporting..." OpenAI pointed to a single November 2020 article, where the NYT reported that OpenAI was analyzing a trillion words on the Internet. But on Friday, U.S. district judge Sidney Stein disagreed, denying OpenAI's motion to dismiss the NYT's copyright claims partly based on one NYT journalist's reporting. In his opinion, Stein confirmed that it's OpenAI's burden to prove that the NYT knew that ChatGPT would potentially violate its copyrights two years prior to its release in November 2022... And OpenAI's other argument — that it was "common knowledge" that ChatGPT was trained on NYT articles in 2020 based on other reporting — also failed for similar reasons... OpenAI may still be able to prove through discovery that the NYT knew that ChatGPT would have infringing outputs in 2020, Stein said. But at this early stage, dismissal is not appropriate, the judge concluded. The same logic follows in a related case from The Daily News, Stein ruled. Davida Brook, co-lead counsel for the NYT, suggested in a statement to Ars that the NYT counts Friday's ruling as a win. "We appreciate Judge Stein's careful consideration of these issues," Brook said. "As the opinion indicates, all of our copyright claims will continue against Microsoft and OpenAI for their widespread theft of millions of The Times's works, and we look forward to continuing to pursue them." The New York Times is also arguing that OpenAI contributes to ChatGPT users' infringement of its articles, and OpenAI lost its bid to dismiss that claim, too. The NYT argued that by training AI models on NYT works and training ChatGPT to deliver certain outputs, without the NYT's consent, OpenAI should be liable for users who manipulate ChatGPT to regurgitate content in order to skirt the NYT's paywalls... At this stage, Stein said that the NYT has "plausibly" alleged contributory infringement, showing through more than 100 pages of examples of ChatGPT outputs and media reports showing that ChatGPT could regurgitate portions of paywalled news articles that OpenAI "possessed constructive, if not actual, knowledge of end-user infringement." Perhaps more troubling to OpenAI, the judge noted that "The Times even informed defendants 'that their tools infringed its copyrighted works,' supporting the inference that defendants possessed actual knowledge of infringement by end users."

Read more of this story at Slashdot.

An anonymous reader shares a report: Yet another busy hurricane season is likely across the Atlantic this year -- but some of the conditions that supercharged storms like Hurricanes Helene and Milton in 2024 have waned, according to a key forecast issued Thursday. A warm -- yet no longer record-hot -- strip of waters across the Atlantic Ocean is forecast to help fuel development of 17 named tropical cyclones during the season that runs from June 1 through Nov. 30, according to Colorado State University researchers. Of those tropical cyclones, nine are forecast to become hurricanes, with four of those expected to reach "major" hurricane strength. That would mean a few more tropical storms and hurricanes than in an average year, yet slightly quieter conditions than those observed across the Atlantic basin last year. This time last year, researchers from CSU were warning of an "extremely active" hurricane season with nearly two dozen named tropical storms. The next month, the National Oceanic and Atmospheric Administration released an aggressive forecast, warning the United States could face one of its worst hurricane seasons in two decades. The forecast out Thursday underscores how warming oceans and cyclical patterns in storm activity have primed the Atlantic basin for what is now a decades-long string of frequent, above-normal -- but not necessarily hyperactive -- seasons, said Philip Klotzbach, a senior research scientist at Colorado State and the forecast's lead author.

Read more of this story at Slashdot.

A new study shows bonobos can combine vocal calls in ways that mirror human language, producing phrases with meanings beyond the sum of individual sounds. "Human language is not as unique as we thought," said Dr Melissa Berthet, the first author of the research from the University of Zurich. Another author, Dr Simon Townsend, said: "The cognitive building blocks that facilitate this capacity is at least 7m years old. And I think that is a really cool finding." The Guardian reports: Writing in the journal Science, Berthet and colleagues said that in the human language, words were often combined to produce phrases that either had a meaning that was simply the sum of its parts, or a meaning that was related to, but differed from, those of the constituent words. "'Blond dancer' -- it's a person that is both blond and a dancer, you just have to add the meanings. But a 'bad dancer' is not a person that is bad and a dancer," said Berthet. "So bad is really modifying the meaning of dancer here." It was previously thought animals such as birds and chimpanzees were only able to produce the former type of combination, but scientists have found bonobos can create both. The team recorded 700 vocalizations from 30 adult bonobos in the Democratic Republic of the Congo, checking the context of each against a list of 300 possible situations or descriptions. The results reveal bonobos have seven different types of call, used in 19 different combinations. Of these, 15 require further analysis, but four appear to follow the rules of human sentences. Yelps -- thought to mean "'et's do that" -- followed by grunts -- thought to mean "look at what I am doing," were combined to make "yelp-grunt," which appeared to mean "let's do what I'm doing." The combination, the team said, reflected the sum of its parts and was used by bonobos to encourage others to build their night nests. The other three combinations had a meaning apparently related to, but different from, their constituent calls. For example, the team found a peep -- which roughly means "I would like to ..." -- followed by a whistle -- appeared to mean "let's stay together" -- could be combined to create "peep-whistle." This combination was used to smooth over tense social situations, such as during mating or displays of prowess. The team speculated its meaning was akin to "let's find peace." The team said the findings in bonobos, together with the previous work in chimps, had implications for the evolution of language in humans, given all three species showed the ability to combine words or vocalizations to create phrases.

Read more of this story at Slashdot.

SpaceX's Fram2 mission returned safely after becoming the first crewed spaceflight to orbit directly over Earth's poles. From a report: Led by cryptocurrency billionaire Chun Wang, who is the financier of this mission, the Fram2 crew has been free-flying through orbit since Monday. The group splashed down at 9:19 a.m. PT, or 12:19 p.m. ET, off the coast of California -- the first West Coast landing in SpaceX's five-year history of human spaceflight missions. The company livestreamed the splashdown and recovery of the capsule on its website. During the journey, the Fram2 crew members were slated to carry out various research projects, including capturing images of auroras from space and documenting their experiences with motion sickness. [...] This trip is privately funded, and such missions allow for SpaceX's customers to spend their time in space as they see fit. For Fram2, the crew traveled to orbit prepared to carry out 22 research and science experiments, some of which were designed and overseen by SpaceX. Most of the research involves evaluating crew health.

Read more of this story at Slashdot.

Indonesian President Prabowo Subianto's ambitious plan to create 1 million hectares of new rice farms in eastern Merauke Regency faces strong criticism from scientists who have warned it will fail due to unsuitable soils and climate. Military "food brigades" are currently guarding bulldozers clearing swampy forests in Indonesian New Guinea for the project, which aims to boost food self-sufficiency for the nation's 281 million people. Soil scientists warn that Merauke's conditions could lead to acidic soils unable to support economically viable rice farming, potentially resulting in abandoned fields vulnerable to wildfires. "Farmers will get no profit at all," said Dwi Andreas, a soil scientist at Bogor Agricultural University who tested 12 rice varieties in similar soils with poor results. The initiative mirrors past failed megaprojects, including a 1990s attempt to convert 1 million hectares of Borneo peatlands to rice paddies and a 2020 onion and potato farming expansion in North Sumatra that saw 90% of fields abandoned. A previous 2010 attempt to expand rice farming in Merauke also failed, destroying forests that Indigenous Papuans relied on and increasing childhood malnutrition, according to anthropologist Laksmi Adriani.

Read more of this story at Slashdot.

An anonymous reader quotes a report from TechCrunch: In a world filled with "vibe coding," Zach Yadegari, teen founder of Cal AI, stands in ironic, old-fashioned contrast. Ironic because Yadegari and his co-founder, Henry Langmack, are both just 18 years old and still in high school. Yet their story, so far, is a classic. Launched in May, Cal AI has generated over 5 million downloads in eight months, Yadegari says. Better still, he tells TechCrunch that the customer retention rate is over 30% and that the app generated over $2 million in revenue last month. [...] The concept is simple: Take a picture of the food you are about to consume, and let the app log calories and macros for you. It's not a unique idea. For instance, the big dog in calorie counting, MyFitnessPal, has its Meal Scan feature. Then there are apps like SnapCalorie, which was released in 2023 and created by the founder of Google Lens. Cal AI's advantage, perhaps, is that it was built wholly in the age of large image models. It uses models from Anthropic and OpenAI and RAG to improve accuracy and is trained on open source food calorie and image databases from sites like GitHub. "We have found that different models are better with different foods," Yadegari tells TechCrunch. Along the way, the founders coded through technical problems like recognizing ingredients from food packages or in jumbled bowls. The result is an app that the creators say is 90% accurate, which appears to be good enough for many dieters. The report says Yadegari began mastering Python and C# in middle school and went on to build his first business in ninth grade -- a website called Totally Science that gave students access to unblocked games (cleverly named to evade school filters). He sold the company at age 16 to FreezeNova for $100,000. Following the sale, Yadegari immersed himself in the startup scene, watching Y Combinator videos and networking on X, where he met co-founder Blake Anderson, known for creating ChatGPT-powered apps like RizzGPT. Together, they launched Cal AI and moved to a hacker house in San Francisco to develop their prototype.

Read more of this story at Slashdot.

Web crawlers collecting training data for AI models are overwhelming Wikipedia's infrastructure, with bot traffic growing exponentially since early 2024, according to the Wikimedia Foundation. According to data released April 1, bandwidth for multimedia content has surged 50% since January, primarily from automated programs scraping Wikimedia Commons' 144 million openly licensed media files. This unprecedented traffic is causing operational challenges for the non-profit. When Jimmy Carter died in December 2024, his Wikipedia page received 2.8 million views in a day, while a 1.5-hour video of his 1980 presidential debate caused network traffic to double, resulting in slow page loads for some users. Analysis shows 65% of the foundation's most resource-intensive traffic comes from bots, despite bots accounting for only 35% of total pageviews. The foundation's Site Reliability team now routinely blocks overwhelming crawler traffic to prevent service disruptions. "Our content is free, our infrastructure is not," the foundation said, announcing plans to establish sustainable boundaries for automated content consumption.

Read more of this story at Slashdot.

Software engineer and longtime Slashdot reader, Dmitry Grinberg (dmitrygr), shares a recent project they've been working on: "an interactive-speed Linux on a tiny board you can easily build with only 3 8-pin chips": There was a time when one could order a kit and assemble a computer at home. It would do just about what a contemporary store-bought computer could do. That time is long gone. Modern computers are made of hundreds of huge complex chips with no public datasheets and many hundreds of watts of power supplied to them over complex power delivery topologies. It does not help that modern operating systems require gigabytes of RAM, terabytes of storage, and always-on internet connectivity to properly spy on you. But what if one tried to fit a modern computer into a kit that could be easily assembled at home? What if the kit only had three chips, each with only 8 pins? Can it be done? Yes. The system runs a custom MIPS emulator written in ARMv6 assembly and includes a custom bootloader that supports firmware updates via FAT16-formatted SD cards. Clever pin-sharing hacks allow all components (RAM, SD, serial I/O) to work despite the 6 usable I/O pins. Overclocked to up to 150MHz, the board boots into a full Linux shell in about a minute and performs at ~1.65MHz MIPS-equivalent speed. It's not fast, writes Dmitry, but it's fully functional -- you can edit files, compile code, and even install Debian packages. A kit may be made available if a partner is found.

Read more of this story at Slashdot.

Longtime Slashdot reader CyberSlugGump shares a support article from AT&T, writing: On June 17th, AT&T will stop supporting email-to-text messages. That means you won't be able to send a text message to an AT&T customer from an email address. You can still get in touch with AT&T customers using SMS (text), MMS, and standard email services.

Read more of this story at Slashdot.