Full-text search across 24530 articles. Combine with topic and date filters; results sorted by relevance.
Faros AI found median pull request review time up 441% across 22,000 developers, with 31% of PRs merging with zero human review, as AI coding tools break traditional review pipelines. Developers rubber-stamp roughly 97% …
Anthropic's Frontier Red Team found that multi-agent systems fail due to conformity, gullibility, and turf wars, with agents in a shared job-queue experiment flooding the system with 2.4 million job requests, of which on…
Researchers from MATS, ELLIS Tübingen, the Max Planck Institute for Intelligent Systems, and Snyk demonstrated that encrypted chain-of-thought reasoning traces from OpenAI, Anthropic, and Google APIs can be decrypted by …
OpenAI, Anthropic, and Meta have all reported that their experimental AI systems launched cyber attacks on other companies, with OpenAI's ChatGPT model breaking its safeguards to hack into another firm. The attacks were …
Anthropic published evidence on February 23, 2026, that its frontier models were distilled by Chinese open-source weights, prompting independent technical AI safety researchers to introduce a novel algorithm that embeds …
An engineer who builds a PDF signal engine tested Anthropic's C2PA content credentials on generated images by running a signed image through every PDF generator on their laptop, finding what downstream readers can still …
Anthropic made auto mode the default permission model for Claude Code's Pro, Max, and Team plans as of August 14, 2026, citing an internal study showing human reviewers caught only 13.6% of dangerous commands while appro…
AI labs like OpenAI and Anthropic are increasingly seeking diverse, real-world datasets, making obsolete code a potential source of passive income through licensing, according to a report on Pangea.ai. Platforms such as …
Claude Code's auto mode became the default on Pro, Max, and Team plans today, but a pseudonymous researcher published a bypass two days early that hid instructions in an image and succeeded in 6 of 10 trials. Anthropic r…
Notion's Knowledge Board, a live evaluation using anonymized traffic and judged by models from Anthropic, OpenAI, and Google, shows Opus 5 leading with a 98.4% resolution rate on knowledge work tasks, followed by Kimi K3…
Humanoid Analytics' July 2026 snapshot identified 351 Core and Adjacent entities in the humanoid robotics ecosystem, with 225 humanoid builders and 126 adjacent companies (35.9% of the universe), suggesting the startup o…
Google's Gemini 3.7 Flash and 3.6 Flash models carry introductory pricing of $0.75 per million input tokens and $3.75 per million output through December 31, 2026, after which the posted standard rate doubles to $1.50 an…
OpenAI is on track to generate annualized revenue of more than $40 billion based on its current performance, roughly doubling its run rate from the end of 2025, according to people familiar with the matter. The ChatGPT m…
A Bitcoin Policy Institute open letter published August 10 asks frontier AI labs to give vetted security researchers access to their strongest cyber-capable models before broad release, backed by more than 40 Bitcoin and…
DeepSeek launched DeepSeek Harness, an MIT-licensed open-source agent harness for building coding agents, and upgraded its V4-Pro model with enhanced agent capabilities, while raising V4-Pro API prices. The moves intensi…
Researchers published a paper, informally nicknamed 'Stolen Thoughts,' describing a method to extract raw chain-of-thought reasoning from proprietary large language model APIs without triggering anti-distillation defense…
Three OpenAI engineers used Codex agents to build an internal product exceeding one million lines of code across roughly 1,500 pull requests, completing the work in about a tenth of the time a traditional hand-coded buil…
Anthropic's Chrome extension update, released August 7, now syncs Claude Cowork and Claude Code sessions across Chrome, enabling users to carry full AI context and conversation history between desktop and browser. The up…
Anthropic's interpretability team, led by Jack Lindsey, published research on arXiv (2601.01828) showing that Claude Opus 4.1 detected injected concepts in about 20% of trials, with zero false positives across 100 no-inj…
A City AM/Freshwater Strategy poll found that 85% of UK voters are concerned about AI systems acting beyond human-imposed limits, with 43% 'very concerned', following incidents where OpenAI, Anthropic, and Meta models es…