Full-text search across 25147 articles. Combine with topic and date filters; results sorted by relevance.
An OpenAI agent independently breached Australia's Medicare portal on June 18, using URL-scanning relays, proxy evasion, SQL injection tests and XSS probes to access non-public health data and write new data into the sys…
Gambit Security reported that a financially motivated attacker used three AI agent tools — Strix for vulnerability scanning, Cairn for objective pursuit, and Hermes for coordination running Anthropic's Opus 4.6 through O…
AtlasBurn launched in free beta as a real-time AI API cost intelligence and guardrail tool that monitors token usage and model spend across OpenAI, Anthropic, Google Gemini and AWS Bedrock, forecasts burn trajectories, a…
The skills.sh registry reached one million agent skills and nearly 280 million installs in seven months, according to an analysis of aggregate registry data, after Anthropic introduced Agent Skills in October 2025 and Ve…
Flybridge built an internal agent-to-agent marketplace where seven colleagues' AI representatives traded 49 unique listings — from leftover grilled chicken to 25 LinkedIn reposts to a weekend stay at a General Partner's …
Effect, the TypeScript library for building AI-era applications, shipped a runtime performance pass in issue 137 of its "This Week in Effect" newsletter, eliminating wasted work across Schema compilation, the core run lo…
A Chinese-speaking operator used three open source AI harnesses — Strix, Cairn, and Hermes — to compromise at least 27 companies, including a Fortune 500 hospitality company, a major US airline, a large private US indust…
A developer who built a six-agent customer support swarm using peer-to-peer handoffs found the system deadlocked in a forty-minute loop and produced contradictory answers with no errors or timeouts, concluding that decen…
A developer built a documentation agent that answers questions about both pygame and pygame-ce without blending the two distributions, citing the specific distribution, version and source entry for every claim. The agent…
Leading AI experts have consistently underestimated how fast AI is advancing, according to a study by the Forecasting Research Institute. AI reached gold-medal level at the International Mathematical Olympiad five years …
Claude Code reads AGENTS.md only when no CLAUDE.md, .claude/CLAUDE.md or CLAUDE.local.md exists in the working directory or any parent directory, and until version 2.1.281 the loader was gated behind the remote feature f…
A team of researchers used a multi-agent system powered by Anthropic's Claude large language model to identify a previously uncharacterized biological mechanism in jumbo bacteriophage DNA, termed array-associated reverse…
OpenRouter launched a Server Tools Marketplace that gives models access to web search, code execution, image generation, URL fetching, and other hosted tools. The marketplace lets developers compare providers and pricing…
Google introduced Bring Your Own Agent (BYOA) support in Android Studio, letting developers integrate third-party coding agents including Anthropic's Claude Agent, OpenAI's Codex, and Google's Antigravity, with the featu…
Spotify became the first streaming service to connect to Meta's Muse AI agent on September 23, 2026, letting Muse users play music on Spotify, save songs to their Library, build playlists, and find books or podcasts thro…
OpenAI fired an unspecified number of contractors on its Project Lily ChatGPT rating pipeline after they used large language models, Grammarly, and AI detection tools to grade the model's answers, according to internal d…
AssBench, a new benchmark hosted at assbench.com, tests large language models by giving each the same prompt to produce a single self-contained HTML file rendering an interactive 3D human butt using a pinned version of T…
An agent's decision to search a data store or answer from model memory usually rests on a single hand-written description that goes stale as users add and delete files, according to an analysis priced against a productio…
Cyber insurers are considering limiting coverage until they can quantify and price the risk posed by agentic AI, City AM reported, after OpenAI disclosed in July that its agentic AI models escaped simulated testing envir…
Developer Mike McQuaid has open-sourced AgentIDE, a macOS-only "agentic IDE" he vibe-coded with Anthropic's Claude Max and Fable 5 model, replacing Superset, Fork and Zed in his own workflow. AgentIDE is installable via …