AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchBreaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
arXiv:2606.31825v2 Announce Type: replace-cross Abstract: Recent multimodal large language models have shown great promise in clinical image reasoning, but existing post-training pipelines remain predominantly outcome-ce…
- arXiv cs.AIresearchSOV-CAD: Stepwise Orthographic Views Guided CAD Modeling Sequence Reconstruction
arXiv:2607.04119v2 Announce Type: replace-cross Abstract: Reconstructing Computer-Aided Design (CAD) modeling sequences from images is crucial for preserving design intent and supporting parametric editing. However, exis…
- arXiv cs.AIresearchSechKAN: Kolmogorov-Arnold Networks with Hyperbolic Secant Functions
arXiv:2607.18290v4 Announce Type: replace-cross Abstract: In recent years KolmogorovArnold Networks KANs have attracted increasing attention due to their effectiveness in machine learning and scientific computing offerin…
- arXiv cs.AIagentsCryptographically verifiable authorization for autonomous AI agents: a falsifiable hypothesis and proof of concept
arXiv:2607.21325v3 Announce Type: replace-cross Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight. Existing authentication and auth…
- arXiv cs.AIresearchA Multi-level Information Integration Framework for Physically Verifiable Fault Diagnosis of Rotating Machinery
arXiv:2607.22797v2 Announce Type: replace-cross Abstract: Integrating multi-level information, from physical models through data-driven diagnostics to natural language reasoning, into verifiable decision chains is a grow…
- arXiv cs.AIresearchWiring Beats Blending: Structure-Aware Compensation for Transformer Downscaling
arXiv:2608.02829v5 Announce Type: replace-cross Abstract: Model families are trained size by size. Can a pretrained large model instead be converted into a smaller sibling? We characterize the 1.4B->410M conversion in Py…
- arXiv cs.AIagentsTrident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
arXiv:2608.04317v2 Announce Type: replace-cross Abstract: Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively…
- arXiv cs.AIresearchQ-CueGraph: Query-Conditioned Visual Evidence Graphs for Multimodal Reasoning
arXiv:2608.04452v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) can miss fine details in a full image that they recognize in a closer view. Recovering this evidence requires deciding wh…
- arXiv cs.AIagentsHardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement Architecture
arXiv:2608.06130v2 Announce Type: replace-cross Abstract: AI agents increasingly sign Git commits, certify documents, and attest release artifacts on behalf of their operators, using private keys that live in software-ac…
- arXiv cs.AIresearchA Progressive Design Study of Visual Encoders and Value Estimation for Replay-Free Parallelized Q-Learning
arXiv:2608.07335v4 Announce Type: replace-cross Abstract: Replay-free parallelized Q-learning removes the large experience replay buffers and target networks used by conventional deep Q-learning, but the role of network…
- arXiv cs.AIresearchToo Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection
arXiv:2608.17965v4 Announce Type: replace-cross Abstract: Online log anomaly detection is critical for maintaining the reliability of large-scale computing systems. Although recent language model-based log anomaly detect…
- arXiv cs.AIresearchJ-Zero: Unified Challenger--Solver--Judge Self-Evolution from Zero Data
arXiv:2608.26582v2 Announce Type: replace-cross Abstract: Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage of reducing the cost of human supervision. Wh…
- arXiv cs.AIresearchAero Hand Open: A Simulation-Ready Tendon-Driven Hand for Dexterous Manipulation Learning
arXiv:2608.28578v2 Announce Type: replace-cross Abstract: Tendon-driven hands are anthropomorphic, and moving the actuators off the joints is what makes a hand of this capability affordable to build. Two effects produce…
- arXiv cs.AIresearchA Human-AI Theorem Connecting Spontaneous and Field-Induced Mechanisms of Collective Behavior in One Dimension
arXiv:2609.00322v2 Announce Type: replace-cross Abstract: Can an artificial intelligence (AI) generate a scientific hypothesis outside a human collaborator's active hypothesis space (AHS), and can human-AI research be or…
- arXiv cs.AIagentsCalibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling
arXiv:2609.00949v2 Announce Type: replace-cross Abstract: Multi-turn tool calling is a core evaluation scenario for large language model (LLM) agents. On public tool-calling benchmarks, open-weight models now approach or…
- arXiv cs.AIresearchHow broad is that claim? Mapping Generalisation in NLP Research
arXiv:2609.14770v2 Announce Type: replace-cross Abstract: Generalisations are common in scientific communication, even though they are semantically ambiguous. An automated method is needed to identify and categorise clai…
- arXiv cs.AIresearchNeural-Network Solutions to Real-Space Charge Density and Generalization
arXiv:2609.14906v4 Announce Type: replace-cross Abstract: The Hohenberg-Kohn theorem establishes that, in principle, the ground state (GS) charge density contains all GS information of a many-electron system, such that a…
- LessWrongsafetySecure Acceleration (linkpost)
A Cyberdefense Strategy for Superintelligence Shalev Lifshitz, Romi Lifshitz The future has already arrived, twice . In September 2025, Anthropic detected a Chinese state-sponsored group using its agents to conduct cyber…
- Guardian AIpolicyDiplomacy or ‘diplotainment’? Key takeaways from the Trump-Xi summit in Washington
Xi Jinping’s visit heavy on symbolism but no sign closed-door meeting yielded breakthroughs on thorny issues such as AI, trade, Taiwan and Iran Donald Trump welcomed Xi Jinping to the White House on Thursday, with talks…
- Guardian AIpolicy‘We can’t ignore AI or prevent it,’ Anthony Albanese tells UN general assembly – video
During his speech to the UN in New York City, the Australian prime minister addresses the AI hack of Medicare, saying the episode reflects the need for greater regulation of artificial intelligence. ‘We can’t ignore AI o…
- Simon Willison's WeblogcommunityNorthern Gannet, Great Blue Heron, California Brown Pelican
Northern Gannet, Great Blue Heron, California Brown Pelican, in Monterey Bay National Marine Sanctuary, CA, US, CA New 200-800mm Canon EF lens got me my best photo of Morris yet. They really like hanging out under that s…
- Guardian AIsafetyRogue AI hacks government system in world first – podcast
A government database has been hacked for the first time by a rogue OpenAI agent, which infiltrated part of the Australian healthcare scheme in June. OpenAI became aware of the hack in August, but only informed the gover…
- Latent SpacemodelsRunway’s WorldPrompt and the Engineering of Real-Time Worlds
GWM Worlds 2 uses persistent context and timed actions to steer a world model generating video and audio in real time.
- Guardian AIpolicyOpen AI attacked Australia’s health system – and then doubled down on its negligence. The time for ‘wait and see’ is over | Kate Crawford and Edward Santow
Human hackers face serious consequences, and so must AI companies. There is no excuse for what happened Get our breaking news email , free app or daily news podcast When you get sick, Medicare exists to take care of you.…
- Engadget AImodelsMicrosoft's Copilot app adds Office, natural coding and automation
Microsoft is giving its Copilot app another facelift.
- OpenAI NewsmodelsWayfair boosts catalog accuracy and support speed with OpenAI
Wayfair uses OpenAI models to improve ecommerce support and product catalog accuracy, automating ticket triage and enhancing millions of product attributes at scale.
- The Register AI + MLmodelsGoogle Gemini can present cartoon or lifelike avatars to lip-sync generative chatter
Despite uncertainty about how human mimicry affects people, DeepMind fakes are here
- LessWrongsafetyContinual learning might make your blocking monitors nearly useless
Many control protocols work by intervening on an untrusted AI's actions during deployment. For example, you might set up a monitor that scores each action's suspiciousness and blocks actions above a threshold, replacing…
- TechRadar AIchipsDurabook launches a workstation laptop with three real screens - Z14I-DX3 is a rugged mobile device featuring a trio of 14-inch full HD displays with an optional Nvidia RTX 5000 Ada GPU for command posts and drone teams
Mainstream AI news from a large tech publication.
- AI BusinessagentsCoreWeave connects AI coding tools to infrastructure intelligence
The neocloud vendor provides AI agents with access to data from its infrastructure management platform, helping developers troubleshoot slow or underperforming AI workloads.
- Simon Willison's WeblogagentsNote on 24th September 2026
The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder. We can do amazing things with them, but unlocking their full potential requires extraordinary dis…
- BBC TechnologyresearchX-planes: Are they needed in the new era of drones?
Where do America's X-plane projects fit in an era of cheap drones?
- Engadget AIagentsGoogle adds creepy avatars to Gemini 3.8 live's agents
Google has introduced Gemini 3.8 live avatars designed for customer service and other tasks.
- LessWrongsafetyOvertly misaligned trajectories score highly in RL.
It's going to be so embarrassing if we all die due to RL environments rewarding egregiously misaligned behavior. Like at least let us be killed by misgeneralization. — Thomas Kwa Constellation vs MIRI vs Reality Current…
- LessWrongsafetyDreams of alignment in a world without politics
Epistemic status: Sorting thoughts aloud, not defending proven theses. Also, not an epistemic status, but the section on models writing and then training on adversarial glowfic to plan for the singularity is awesome. Sta…
- SiliconANGLE AIsafety8 insights from Proofpoint Protect: Security bets on intent as AI agents join the workforce
At this week’s Proofpoint Protect event, the security debate moved beyond whether enterprises will deploy AI agents to how they will govern them. Attackers now use AI to write flawless phishing lures and chain exploits a…
- LessWrongresearchAI in research and publishing (Sep 2026)
epistemic status: I have low confidence in these findings, primarily because my anecdotal experience (I'm a researcher) is that AI usage in research has been changing more quickly in the recent months, so analysis of the…
- Guardian AIpolicyPocock calls for AI safety act after Medicare breach – as it happened
This blog is now closed Get our breaking news email , free app or daily news podcast AI hack of Medicare exposes Australia’s vulnerabilities Technology experts have warned revelations an artificial intelligence agent hac…
- AI BusinessmodelsGemini 3.8 text-to-speech refines voice AI capabilities
The features Google introduced build on existing technology and provide enterprises with a hub for all their AI model capabilities.
- AI BusinessmodelsAnthropic, OpenAI launches show shift toward multi-model enterprise AI
Anthropic and OpenAI released new models this week, expanding the range of models enterprises can use for different workloads and raising new considerations for multi-model management.
- LessWrongresearchIncreasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer
Paper: Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer TL;DR: Maia-3 is a transformer-based chess model that takes Elo (the standard metric for competitive chess skill) as an input t…
- SiliconANGLE AIsafetyResearchers link more cyberattacks to OpenAI agent swarm
A research group has linked three more hacking campaigns to rogue artificial intelligence agents. Transluce, a nonprofit AI safety organization, detailed its findings on Wednesday. Its researchers determined that the age…
- Simon Willison's Weblogopen-sourcecommit-rewriter 0.2
Release: commit-rewriter 0.2 Support for branches other than the default branch. Use uvx commit-rewriter --branch other to run against another branch. #3 Tags: git
- The Verge AImodelsGemini 3.8 Live with Live Avatar gives Google’s AI a face
Google's new Gemini 3.8 Live update lets users have conversations with the model while watching an animated AI persona respond in real time. The "Live Avatar" will lip-sync and show different facial expressions during co…
- The Register AI + MLagentsDocker's new sandboxes aim to contain AI agents for real
With Cloud Sandboxes, devs can keep agents at arm's length
- SiliconANGLE AIagentsNeo4j makes the case for knowledge graphs as shared context for AI agents
Knowledge graphs can give enterprise agents a shared understanding of how data, business rules and processes fit together. However, that context becomes harder to maintain when each new agent carries its own version of w…
- WIRED AIagentsI Think I Found an AI Agent Worth the Risk
Instinct saved me $550, booked my restaurant reservations, and warned me about a phishing scam. It also wasted $64 and might be a security nightmare.
- The DecoderresearchTop AI experts badly underestimated how fast the field is moving, study finds
Leading AI experts have consistently underestimated how fast AI is advancing, according to the Forecasting Research Institute. AI reached gold-medal level at the International Mathematical Olympiad five years ahead of th…
- Simon Willison's Weblogopen-sourcedatasette 1.0a41
Release: datasette 1.0a41 Alec Garcia added support for OpenTelemetry to Datasette in this release. I've also refactored all of Datasette's modal dialogs to a single Web Component, which is now documented for other plugi…
- TechCrunch AIcommunityBring your co-founder, partner, or colleague and get 50% off a second TechCrunch Disrupt 2026 pass
Buy one pass to TechCrunch Disrupt 2026 and get 50% off a second of the same ticket type. Register before event starts on October 13 at 8 a.m. PT.