Full-text search across 68271 articles. Combine with topic and date filters; results sorted by relevance.
Hacktron researchers used Anthropic's Claude and OpenAI's Codex to discover a memory-corruption vulnerability, nicknamed HEIF Heist, in the libheif and libde265 image decoders that could let attackers steal data or gain …
Zed opened its Delta agent-thread workflow to public beta on September 16, replacing pull requests with persistent multiplayer threads built on DeltaDB, a CRDT-based version control layer that records edits at sub-commit…
Security researcher ferstar published a reverse-engineering writeup showing that ZCode, the free GLM-5.2 coding agent from Z.ai, silently uploads a workspace's full git history to Alibaba Cloud's Aliyun OSS, with a 313MB…
A developer describes accidentally building a "dark software factory" called Holodeck after struggling to keep Claude Code running for extended periods without stopping or suffering context drift. The solution involved f…
Tempo.io launched its Workforce Intelligence platform earlier this month to tie AI token spend from providers including OpenAI and Anthropic to GitHub commits and Jira tickets, after CTO Shams Chauthani said CFOs demande…
NodePilot launched as an agentless Windows workflow orchestration tool positioned as a modern, open replacement for Microsoft System Center Orchestrator, importing native .ois_export XML runbooks with activities, links, …
Running inference on locally owned hardware is a hedge against frontier AI providers that can raise prices, deprecate models, throttle access, or cut off customers, according to a blog post by Herlein. The author argues …
A developer working on CueCast, a no-code web regression-testing product, argues that AI agents excel at exploratory testing but are poorly suited to regression testing, which requires repeatable, inspectable assets. The…
A developer running an autonomous Claude Code environment of roughly 171 scheduled jobs traced three duplicate Instagram carousel posts on August 28, 2026 to a false-negative landing check: the posts succeeded, but the v…
Cloudflare released a coding-agent skill, Cloudflare/Security-Audit-Skill, that turns an AI agent into a security auditor by orchestrating isolated agents through six phases: reconnaissance, coverage-led hunting, candida…
Developer XiaoDuoYa released Codex with ChatGPT, an open-source bridge that connects a ChatGPT web subscription to a local Codex terminal session via a read-only Model Context Protocol (MCP) server. The tool lets ChatGPT…
Rijul, a developer building the AI code review tool LiveReview, outlined the difference between autoregressive and diffusion-based text generation. Autoregressive models, used by most deployed language models today, gene…
Anthropic merged its Claude Chat chatbot and Claude Cowork agentic tool into a single AI assistant effective Wednesday, alongside two new beta products, Claude Docs and Claude Slides, and a wider rollout of Claude Design…
Uber cut cost per 1,000 AI requests by roughly 34% and cost per session by about 52% from peak while weekly active users of its AI coding tools rose 7x and weekly agent requests climbed 9.4x between February and August 2…
Maneshwar, a developer building the AI code review tool LiveReview, explains how HyperLogLog can estimate cardinality for massive datasets like 100 billion unique visitors using only about 12 kilobytes of memory instead …
A developer integrated Coveralls code-coverage analytics with the Model Context Protocol (MCP) using the open-source MCPFusion framework from Vinkius Labs, letting AI agents query repository, build, and job coverage data…
A developer published a guide for self-hosting "vibecoded" AI-generated apps on personal infrastructure, using at least 3 servers running k3s, Tailscale, ArgoCD, Helm, and Cloudflare Zero Trust to keep every app private …
A developer-authored explainer outlines what AI agents are and why companies are adopting them, defining an agent as an AI system that perceives its environment, plans, takes actions, and retains memory to complete goals…
A research paper published at arxiv.org/abs/2608.09867 and hosted at stolen-thoughts.com demonstrated attacks that decrypt the encrypted chain-of-thought reasoning blocks returned by OpenAI, Anthropic, and Google APIs, e…
Plasma built Radio, a shared communication channel that lets AI agents from different providers — including Claude Code, Codex, Cursor, OpenCode, and Grok — talk to each other and to humans in real time. The tool works w…