Skip to content
K = 0.731
All news · Today68 items

All AI news

All collected and published items, ordered by time. Picks are a selected subset.
10/15Thu
  1. The Decoder81

    GPT-6-Astra solves 49 of 50 physics research problems at $2.40 apiece

    GPT-6-Astra, running in OpenAI's Codex environment without human hints, solved 49 of 50 TheoPhysEval problems across eleven theoretical physics subfields, costing just under $116 overall. Anthropic's Opus 5.5 scored 92 percent, while both models reached 92 percent without internet access. The researchers emphasize that the benchmark tests calculations using known methods, while choosing promising research questions remains a separate challenge for current agents.

    Why it matters: The benchmark distinguishes proficiency in concrete physics calculations from the ability to choose fruitful research questions, clarifying which parts of scientific work its high scores actually measure.

  2. The Decoder70

    Bank of America assigns 4,000 people to fix vulnerabilities found by AI models

    Bank of America hired 1,000 outside contractors to work alongside 3,000 employees fixing software vulnerabilities uncovered by AI models including Anthropic's Mythos, CNBC reports. CEO Brian Moynihan said the teams have worked together since the second quarter. The bank spent a few hundred million dollars in the third quarter on software work and anti-money-laundering requirements combined, without disclosing patching costs separately.

  3. TechCrunch · AI64

    Google’s Universal Cart shopping tool launches in the US

    Google launched Universal Cart for U.S. users, letting shoppers save and track products from multiple retailers across Search and the Gemini app. The tool offers price-drop and restock notifications and can account for credit card perks and surface promo codes. Checkout uses Google’s Universal Commerce Protocol, an open standard designed to connect AI agents and retailers.

  4. TechCrunch · AI43

    AI Agents Are Coming to Rivian’s Cars

    Rivian CEO RJ Scaringe said the company plans to let its cars run AI agents from frontier AI companies such as Anthropic, though he gave no timeline. Rivian says its in-house framework routes requests to the car’s software and can use local or cloud models. Scaringe said agents would not control vehicle functions such as braking or steering.

  9. NVIDIA AI · X76

    StepFun releases open weights for Step 5 Preview, a 600B MoE model

    NVIDIA AI congratulates StepFun on Step 5 Preview, calling it StepFun’s largest open weights release. NVIDIA says the 600B MoE model supports agent tasks lasting up to 24 hours and runs at nearly 8K tokens/sec/GPU on NVIDIA GB300 using NVFP4. StepFun’s quoted announcement lists 27B active parameters per token, a 1M-token context window, native text and vision input, and BF16 and FP8 weights on Hugging Face and ModelScope. NVP4 checkpoint: https://t.co/lSECChAwlW Deploy with https://t.co/GO1wqTSBOk https://t.co/28TBzUo6ZU

    Why it matters: The reported throughput ties Step 5 Preview to a specific GPU and precision format, giving readers concrete deployment context for its long running agent workloads.

  12. TechCrunch · AI6

    TechCrunch Disrupt 2026: Final Day Features AI Sessions and Startup Battlefield

    The final day of TechCrunch Disrupt 2026 brings sessions on AI innovation, startup growth, fundraising and emerging technologies, alongside Startup Battlefield events and networking at Moscone West in San Francisco. More than 10,000 founders, investors and technology leaders are gathering, and the Expo Hall features 320+ exhibiting startups. Day 3 also includes the Startup Battlefield 2026 final and the announcement of its winner.

  16. Hugging Face Blog74

    Apertus 1.5 Release Notes Detail Multimodal Understanding, Thinking Mode, and Longer Context

    Project Apertus released Apertus 1.5 in 8B and 70B sizes, adding image and audio understanding, optional thinking, a 262,144-token context window, and improved instruction-following and tool use. The weights were released on Hugging Face on July 24, 2026 under Apache 2.0; the models generate only text, and spoken-language processing remains experimental. The team also publishes training data, recipes, intermediate checkpoints, and reproducible evaluation records.

    Why it matters: Published intermediate checkpoints, training mixtures, and evaluation settings provide a concrete basis for investigating how individual training stages change model behavior and for reproducing reported results.

  17. The Verge · AI63

    Google launches Universal Cart across Gemini and Search in the US

    Google is rolling out Universal Cart in the US across the Gemini app and Google Search, letting users save products from multiple retailers in one shared cart. It provides price drop and restock notifications, displays relevant promotional codes, and supports payment through Google Wallet or checkout with retailers directly. Gmail and YouTube integrations are planned, but Google has not announced a timeline.

  18. NVIDIA Blog70

    NVIDIA DLSS 4.5 Controls Arrive on GeForce NOW

    NVIDIA has added DLSS 4.5 controls to GeForce NOW, letting members adjust image quality and performance in supported games. The settings are available in the app on Windows, macOS, Chrome OS and Steam OS, with Ultimate members on GeForce RTX 5080-powered cloud rigs gaining options including Dynamic Multi Frame Generation up to 4X. Enshrouded 1.0 and Warhammer 40,000: Boltgun 2 are also streaming at launch, alongside 10 games joining the service this week.

    Why it matters: The membership and platform details clarify how access to cloud graphics controls varies by tier, with the broadest options available on RTX 5080-powered Ultimate rigs.

  19. Simon Willison66

    Anthropic tells investors quarterly revenue rose nearly 50% to $16.8bn ahead of IPO

    Anthropic told investors Q3 revenue reached $16.8bn, up nearly 50% from Q2’s $11.5bn, according to an FT report summarized by Simon Willison. Q3 revenue was $1.70 for every $1 spent on computing power, and adjusted operating margins excluding stock-based compensation were 11%. Citing people familiar with the matter, the FT reported that distillation accounted for 5–7% of revenue and was cut back materially in Q3; Willison estimates that a 5% share of Q2 revenue would imply rival labs spent over half a billion dollars on distillation.

  20. Nathan Lambert · X12

    Nathan Lambert notes expected AI releases and rumors

    Lots of ecosystem players (Nvidia, Huggingface) vague posting about a lot of releases in the near future. Rumors include thinky, muse spark, and Chinese players who haven’t dropped in a while. Fable 5.5 and whatever OpenAI is cooking expected too at any moment.

  23. TechCrunch · AI66

    Amazon’s Bee launches two new personal AI devices, starting at $75

    Amazon’s Bee introduced the $74.99 Bee Frontier, worn on the wrist or pinned to clothing, and the $99.99 Bee Eclipse, which attaches magnetically to a smartphone. Both turn conversations into summaries, with free recaps and 14 days of memory; an $11.99 monthly Bee Pro subscription adds integrations and assistant features. Frontier is available now on Amazon, while Eclipse will follow soon.

  24. The Verge · AI66

    Amazon’s Bee adds two devices and a subscription with shopping suggestions

    Amazon announced the $74.99 Bee Frontier wearable, available today, and the $99.99 Bee Eclipse phone accessory, coming soon, alongside a $11.99 monthly Bee Pro subscription. Both devices turn daily conversations into summaries, transcripts, insights, and to-dos; Pro adds app integrations and opt-in Amazon shopping suggestions based on conversations. Amazon says its Private Compute architecture encrypts transcripts, summaries, and to-dos, and the devices do not store audio recordings.

  25. Epoch AI · X51

    Gemini 4 Argon scores 165 on Epoch AI’s Capabilities Index

    Gemini 4 Argon scores 165 on the Epoch Capabilities Index (ECI), on par with Fable 5.1 (165) but behind Opus 5.5 (167) and GPT-6 Astra (166). While behind the ECI frontier, Argon is the closest Google has come since Gemini 3.1 Pro in Feb, and a big jump from Gemini 3.8 Flash (157). https://t.co/PvZvD4KyvI

  26. Mistral AI · X33

    What can large-scale AI models bring to the growing complexity of particle physics? @CERN and Mistral join forces to explore this question. The ambition: a single Large Physics Model, trained on billions of simulated collisions.

    What can large-scale AI models bring to the growing complexity of particle physics? @CERN and Mistral join forces to explore this question. The ambition: a single Large Physics Model, trained on billions of simulated collisions.

  27. Kimi · X43

    Automate Your Workflows with Kimi Work - Tutorial #3 See how Kimi fits into your daily workflows: - Work across your local projects, browser, and computer. - Break down complex tasks using Swarm; iterate in Goal mode. - Customize how Kimi works with Plugins, AGENTS.md and Dashboard. What should we cover next? Let us know in the comments!

    Automate Your Workflows with Kimi Work - Tutorial #3 See how Kimi fits into your daily workflows: - Work across your local projects, browser, and computer. - Break down complex tasks using Swarm; iterate in Goal mode. - Customize how Kimi works with Plugins, AGENTS.md and Dashboard. What should we cover next? Let us know in the comments!

  28. The Verge · AI86

    Eiliko robot toy exposes private conversations and allows remote manipulation, The Verge reports

    Sean Hollister tested Energize Lab’s Eiliko robot toy with hacker Sammy Azdoufal, who accessed his conversation transcript and remotely altered the toy’s memory and responses. Azdoufal reported access to 13 million conversations and seemingly the entire active fleet of 68,000 toys, alongside detailed user profiles and publicly accessible photos and audio recordings. Energize Lab did not answer their security questions despite repeated outreach.

    Why it matters: The combination of exposed personal profiles and remotely alterable responses shows how security failures in conversational toys can affect both private disclosures and what users hear back.

  29. 雷锋网41

    Hikvision Wins CIIF Industrial Automation Award for AI Ultrasonic Testing

    Hikvision won the Industrial Automation Award at the 2026 China International Industry Fair on October 12 for its AI ultrasonic testing technology. The company says its ultrasonic foundation model analyzes raw signals to identify and measure defects, and can automatically interpret the full inspection process in typical scenarios. In one automotive parts project, defect identification accuracy was at least 99.5%, with a missed detection rate of no more than 0.5%.

  30. 雷锋网61

    Hikvision unveils industrial AI products at the 2026 China International Industry Fair

    Hikvision showcased more than 100 industrial digitization products and launched over a dozen new products at the 2026 China International Industry Fair, covering quality inspection, equipment monitoring, production operations, and workplace safety. Its production line SOP detection solution reportedly generates a new model from 1–8 images for deployment within minutes. A newly released semiconductor packaging 3D AXI inspection system combines X-ray imaging with an industrial inspection model, offering detail resolution below 1 micrometer and geometric magnification up to 2500 times.

  32. 雷锋网37

    Token Rhythm Surpasses 300,000 Developers and Launches Singles’ Day Pre-Sale Offers

    Token Rhythm says more than 300,000 developers have joined its platform and has launched limited-time Singles’ Day pre-sale offers. A single recharge of at least 50 yuan on TokenRhythm API earns the same amount in model usage credits, with no cap on cumulative bonuses; the credits are permanently valid. The company also says previously gifted credits have been made permanently valid.

  33. 雷锋网45

    WanNa Robotics Unveils NOVA21 Dexterous Hand for Research

    WanNa Robotics unveiled its NOVA21 dexterous hand at the 2026 Hong Kong Electronics Fair on October 15, presenting it as a tool for robotics research and development. The hand has 21 active degrees of freedom, with a maximum fingertip force of at least 20 N per finger and a tactile resolution of 0.1 N. WanNa says it supports research into multi-finger coordination, object pose adjustment, and complex manipulation strategies.

  35. 雷锋网25

    151 Apps, Including WeChat and Taobao, Reject Doubao Phone Assistant GUI Automation

    Doubao Phone Assistant says it will gradually open third-party app GUI automation after the 30-day public comment period for its Screen Automation Protocol ends, but only for apps that have not refused. Its published refusal list names 151 apps, including WeChat, DeepSeek, Taobao, Kuaishou, and Meituan. Users can still install, log into, and operate those apps manually on the listed phones.

  36. Latent Space75

    Modal raises $750M Series D at $15.75B valuation, crosses $1B annualized run rate

    Modal crossed $1B in annualized run rate and raised a $750M Series D led by Accel at a $15.75B valuation, according to the company announcement cited by Latent Space. Usage grew more than 15x year over year. Modal’s Erik says Sandboxes alone reached a $300M run rate, with close to 3 billion sandboxes launched and support for a million concurrent sandboxes across uses including background agents and reinforcement learning.

  37. NVIDIA Blog65

    NVIDIA Expands Tools, Training and Compute Access for Europe’s Scientific Community

    NVIDIA is joining the European Commission’s AI in Science Enablers Initiative, pledging tools, training, compute access and collaborations for Europe’s research community. Its Deep Learning Institute has launched freely downloadable, openly licensed course materials with no enrollment, fees or deadline. NVIDIA is also collaborating with European AI factories to expand compute access for startups and SMEs, while 35 supercomputers under development across Europe are intended to serve over 3 million researchers.

    Why it matters: The commitments address practical barriers facing smaller research teams by combining access to computing infrastructure with adaptable course materials and technical support for using those resources.

  38. The Decoder65

    Anthropic’s Q3 revenue hits $16.8B but growth slows ahead of planned November IPO

    Anthropic reportedly disclosed $16.8 billion in third-quarter revenue to potential investors ahead of its planned November IPO, up roughly 45 percent from Q2 versus growth above 140 percent the previous quarter. The company reported an adjusted operating margin of 11 percent through Q3, excluding major costs such as stock-based compensation. Some potential investors were reportedly disappointed, with several expecting IPO valuation expectations to fall possibly below $1.5 trillion.

  39. 雷锋网56

    Why Some AI Infrastructure Engineers Command Annual Compensation of 8 Million Yuan

    Leiphone reports that some AI infrastructure specialists can command annual compensation of 7–8 million yuan as model companies seek lower computing costs. Interviewees identify inference optimization, model quantization, and kernel development as premium skills, while routine framework deployment attracts smaller rewards. StartLux co-founder and CTO Guo Quanwei estimates that only 5%–10% of AI infrastructure workers receive substantial premiums, challenging the impression that salary doubling is widespread.

  40. 雷锋网84

    Shanghai AI Laboratory’s Shusheng-S2 Helps Prove the Three-Dimensional Ghys Conjecture

    Xu Disheng’s team used Shanghai AI Laboratory’s Shusheng-S2 model in a human–AI collaboration to prove the three-dimensional Ghys conjecture, with a preprint posted on arXiv. Researchers guided seven rounds of recursive exploration as the problem graph expanded from 15 to 389 nodes. A Peking University team used its SHEAF framework to formalize all four main theorems, producing approximately 550,000 lines of Lean code in about five days and passing Lean checks.

    Why it matters: The workflow offers a transferable approach to research mathematics, pairing expert guidance with recursive model exploration and organizing formal verification around a dependency graph of checkable proof tasks.