Full-text search across 63994 articles. Combine with topic and date filters; results sorted by relevance.
Rijul, a developer building the AI code review tool LiveReview, outlined why vector search alone is insufficient for retrieval-augmented generation systems and argued for hybrid retrieval. The writeup describes combining…
JetBrains released Qwen3.8-3.6-27B-blend, a merged 27B local coding model that completed 37 of 100 internal coding tasks versus 34 for Qwen3.6 with reasoning disabled and 39 for Qwen3.8, while generating 71% fewer output…
Tencent has open-sourced BrowserSkill, a tool that lets AI coding agents such as Cursor, Claude Code, and Codex drive a user's already logged-in browser without hijacking their active tabs. The system runs a local CLI da…
Vercel Labs released Portless, a CLI tool that replaces localhost port numbers with stable named .localhost URLs via a background reverse proxy daemon that routes requests by hostname. Portless assigns each app an epheme…
OpenCode and OpenRouter launched Union Alpha, a free "stealth" coding model, on September 16 with a 262,144-token context window, text and image input support, and a zero-retention data policy. The model is free during a…
Product teams should treat the software factory as an operating model they can reshape from inside, according to a blog post on agentic engineering by Robert Glaser. The post argues that as AI agents produce more code an…
JetBrains released the Kotlin Benchmark, an official SWE-bench-style evaluation that grades AI coding agents on 105 real repository-level Kotlin engineering tasks, with Claude Code running Opus 4.7 xhigh leading the firs…
Mouse 0.1.0, an open source harness for long-running coding agents built on OpenCode, passed 25 of 30 tasks (83.3%) on FrontierHarness Eval with Kimi K3 on 2026-09-08, at a cost of $2.79 per pass and a median 6m 24s per …
Anthropic released Claude 3.5 Sonnet, a faster and cheaper model than Claude 3 Opus that outperforms it on several key benchmarks, including an internal agentic coding evaluation where it solved 64% of problems versus Op…
Microsoft published a 37-page "humanist AI code of conduct" stating that "people matter more than AI," that AI models are not conscious and "should not be designed to imitate consciousness," and that the company rejects …
A developer built Worktree Switcher, a VS Code extension that lets users instantly switch between Git worktrees for the same repository without opening multiple editor windows. The tool was inspired by Zed's fast-switchi…
A developer released cse-bridge, a self-hosted HTTP service that emulates Google's customsearch/v1 wire format on top of a user's own SearXNG instance, ahead of Google shutting off the Custom Search JSON API on 2027-01-0…
AI coding assistants such as Claude 3.5 Sonnet and GPT-4o let anyone generate a working prototype in ten minutes, but the barrier to quality is unchanged, according to an analysis echoing Paul Ford's argument that AI mak…
AI benchmarks such as BioMysteryBench, GeneBench, and Terminal-Bench 2.1 are inconsequential at best and misleading at worst, according to a deep dive into the scores cited for GPT-5.6, Fable 5.1, and Opus 5. Anthropic r…
A developer contributed three pull requests to the open-source Rowboat project (rowboatlabs/rowboat, 17.5k stars) in roughly 24 hours, fixing an all-day event sorting bug in the sidebar, adding exponential-backoff respaw…
Orca launched as an open-source agent development environment (ADE) that runs coding agents such as Claude Code, Codex, OpenCode, Grok, and Gemini in parallel across isolated workspaces, with a companion mobile app for i…
A developer-authored analysis reports that 76% of frontend developers used at least one AI-driven solution in 2026, with AI design tools cutting prototyping time by over 85% and AI-assisted code completion accounting for…
Systemd 262-rc2, released September 8, added a canary to its AGENTS.md file that instructs AI coding agents to prepend two lines to README.md before modifying source files, with one line only a human submitter can delete…
Combining Claude Projects, which pin a permanent knowledge base of documentation and code to a workspace, with Skills implemented via the Model Context Protocol (MCP) lets developers manage an autonomous development envi…
Researchers Li, Zhang, Hou and coauthors published an arXiv supply-chain study of AI agent harnesses including Claude Code, Codex CLI, OpenCode, OpenClaw, Hermes, OpenHarness and WorkBuddy, describing an attack framework…