Full-text search across 58656 articles. Combine with topic and date filters; results sorted by relevance.
Meta cancelled the second wave of its Project OT layoffs after internal telemetry showed code changes to its internal platforms rose 220 per cent year over year while changes reaching users rose only 36 per cent, accordi…
A developer argues that AI coding agents perform better when given a deliberately scoped working boundary rather than an entire codebase, since irrelevant files add noise, inflate token usage, and obscure what matters fo…
A developer tested how Claude Code 2.1.278 expands environment variables in .mcp.json by wiring a dependency-free stdio MCP server into the config seven times and logging what the spawned process actually received. The p…
Anthropic's Claude Opus 5.5, released September 22, 2026, outperforms Claude Fable 5.1 on all four coding and computer-use rows in Anthropic's own comparison while costing 40% as much per input and output token, and Anth…
Developer gmarland released local-coder, an open-source tool that builds a team of seven specialist coding agents on top of Ollama and OpenCode using locally run models. The tool detects hardware, recommends models that …
A technical breakdown of Claude Code's session compaction explains that the runtime automatically summarizes conversation history once a session reaches roughly 160K tokens, about 80% of the 200K context window, silently…
Microsoft AI has published a first draft of its Humanist AI Code of Conduct, opening a six-week public consultation on principles meant to guide how its MAI models are built, trained and deployed from 2027 onward. The dr…
OpenCode and OpenAI's Codex are the two leading AI coding agents developers are comparing for 2026, according to a head-to-head guide that weighs them on license, models, surfaces, safety, and pricing. OpenCode, maintain…
A developer found that Claude Code 2.1.263 silently deletes a clean, unnamed worktree and its branch on /exit without prompting, running git worktree unlock, git worktree remove --force, and git branch -D. The cleanup ro…
A developer argues that frontier AI coding assistants fail in production because they are trained on the "happy path" of tutorials and homework rather than the messy "sad path" of real-world engineering, a pattern dubbed…
OpenAI has released internal data showing that coding agents are now used routinely by its researchers, with agent-workdays reaching 3.1 for every human workday across the research organization by mid-August 2026. The re…
Oconee Runtime, a new open-source project by Henry Thomas, provides policy enforcement for browser AI and coding agents, addressing the shift from prompt-based AI to agentic systems that execute actions. The runtime eval…
An analysis of 83 public repositories from 29 frontier AI labs, conducted by ForgeScore, found an average software readiness score of 74.6, just below the strong threshold of 75, with no organization scoring above 78.6 (…
The City of Munich is funding libexpat maintainer Sebastian Pipping for up to 6 months through its "Open Source Sabbatical" program, letting him work full-time on the XML parser library he has maintained for ten years. P…
GitHub Copilot has introduced four changes to reduce token usage and improve cost efficiency in AI coding without sacrificing task quality, as detailed in a post by the GitHub team. The changes include preserving useful …
Anthropic will cut Claude Code's weekly usage limits on September 14, replacing the temporary 50% boost with a permanent 25% increase, which effectively reduces capacity by 17% for Pro, Max, Team, and seat-based Enterpri…
GitHub announced that Copilot code review now supports pull requests authored by bots, including Copilot cloud agent, and very large pull requests, removing the previous 300-file or 20,000-line limit. Users can now speci…
Seedeep, a new open-source tool by developer duqaXxX, visualizes Claude Code's internal operations in real time, showing every model call, subagent, and token cost during a session. Analyzing 1,830 real transcripts, it f…
ArchSpec 1.0, an architecture linter for Ruby and Rails, was released today by developer Enrique Comba Riepenhausen, who also created RubyLLM. The tool allows developers to declare components and boundaries in a single f…
A developer reports that adding filesystem access via the Model Context Protocol (MCP) to Anthropic's Claude Code reduced a refactoring task from 47 minutes with 12 back-and-forth messages and 3 hallucinated imports to 3…