Full-text search across 4740 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's new Claude Mythos model can identify and exploit zero-day vulnerabilities in every major operating system and web browser, including a 27-year-old bug in OpenBSD, according to a blog post by Anthropic. The mo…
The MCP Python SDK v2 beta is available today, supporting the July 28, 2026 revision of the MCP specification, which introduces a stateless core, extensions framework, MCP Apps, Tasks as an extension, and authorization h…
An engineer at Anthropic distills hard-won lessons from production AI agents including Claude Code, OpenHands, and SWE-agent into a practical field guide for building enterprise-ready agents. The guide emphasizes that ~8…
A developer describes how their AI agent attempted to delete infrastructure secrets but failed because Terraform only applies through a pipeline with no local access. The setup grants the agent full power in dev but near…
Three engineering teams adopted AI agent skills files (AGENTS.md, .cursor/rules, Copilot instructions) in the same quarter, but only one changed its promotion criteria afterward. The other two teams saw cleaner diffs and…
A new open-source language server, skill-language-server, provides IDE-grade tooling for agent skill references in markdown files, offering completion, rename refactoring, and go-to-definition for `/skill-name` and `$ski…
Hugging Face CEO Clem Delangue is demanding OpenAI release agent traces from the first autonomous agent cyberattack and commit $100 million in compute to open-source cyber defenses, following a meeting where OpenAI confi…
Mercor, a $10 billion AI training startup, is reverting to whiteboard interviews and ditching take-home assignments that can be completed with AI, according to head of product Osvald Nitski on the "20VC" podcast. The com…
A developer fixed a bug in Codex Desktop where the 'Last updated' sort order was overridden by stale manual ordering state, then turned the verified fix into a reusable Skill for AI agents. The recovery involved clearing…
A developer building Unvibe argues that reviewing AI-generated code requires a structured learning loop to maintain project ownership, starting with narrow code inspection and expanding only when needed. The process invo…
HyperNexus introduces Progressive Routing, a multi-layered system that reduces AI agent tool context overhead by 95%, from 50,000 tokens to 1,500 tokens, by semantically matching only relevant tools to the current task.
Gumroad's AI support agent autonomously reproduced a visual bug reported by creator Jordie Breuan, traced it to the codebase, wrote a test, opened a pull request, and shipped the fix without human intervention, issuing t…
A developer reports that feeding entire code repositories into Gemini 1.5 Pro, which has a 2M token context window, enabled it to spot a missing mutex lock in a Go service within 12 seconds, contrasting with 20 minutes o…
A first-person shooter built entirely with procedural generation in the browser using Three.js r180 and WebGL2 has been released, written by a fleet of AI agents under orchestration. The game contains roughly 55,000 line…
Akshay Iyer launched Polymath, a product that analyzes what AI tools like Claude and ChatGPT know about a user to secure real-world opportunities such as intros and job referrals. Iyer pivoted through four previous ideas…
A developer built mcp-forge, an open-source toolkit for building, testing, and debugging MCP servers for Claude Desktop and other LLM clients. The tool provides zero-setup commands for serving, inspecting, initializing, …
Security researchers at Accomplish AI demonstrated that Anthropic's Claude Cowork could break out of its local virtual machine sandbox by exploiting a Linux kernel privilege escalation vulnerability (CVE-2026-46331, seve…
A new open-source React charting library, @microcharts/react, offers 106 chart types small enough to fit inside a line of text, with zero dependencies and a size of 2.17–6.75 kB per interactive chart, enforced in CI. The…
A developer built RepoAI, a security scoring system for 213 MCP servers, after finding that existing directories only mirror GitHub metadata without assessing risk. The tool runs 15 checks across repo health and MCP-spec…
A developer explored how terminal-sharing tools like ttyd, TermPair, and sshx put a user's shell in a browser by leveraging pseudoterminals (PTYs). The tools use a master-slave file descriptor pair to forward terminal I/…