Full-text search across 59703 articles. Combine with topic and date filters; results sorted by relevance.
A developer outlined five recurring failure modes of autonomous coding agents — prompt injection from untrusted file and API content, silent wrong-argument tool calls, runaway plan-act-observe loops, gradual permission c…
Squelette, a project-control layer that sits between humans and AI coding agents, ships at version 3.20.0 as a standard-library Python controller (scripts/project_control.py) that fails closed rather than advising when a…
Anthropic's Claude Code supports user-defined "skills" — reusable procedures stored in a `.claude/skills/<name>/SKILL.md` file — and a worked example shows how to build a release-note skill that reads a local Markdown fi…
A developer released use-citations, an MIT-licensed Claude Code skill that saves source documents, answers research questions from them, and builds a report where each sourced phrase opens a slide-out drawer highlighting…
A developer built three Claude Code skills for AI product managers and published the eval suite, including every failed run, on GitHub. Committing pass criteria to git before testing, the first run of the /build-or-not s…
A developer built CXCAP, an open-source, local, read-only CLI that audits a repository's structural complexity before a coding agent makes a change, aiming to catch coupling and transitive exposure that passing tests mis…
Towards Data Science published an article titled "Your AI Assistant Wrote the Code. Who Checked the Defaults?" examining five scikit-learn defaults that the publication says deserve closer scrutiny before a model reaches…
A developer released claude-profiles, an open-source CLI and Raycast extension that create isolated Claude Desktop accounts and move Claude Code session history between them by rebuilding the per-profile session index. T…
A developer migrated a 90-spec Cypress end-to-end suite to Playwright in four working days using Claude Code, hand-translating one checkout spec first and distilling the patterns into a 14-rule MIGRATION_RULES.md file th…
OpenAI paid a $6,500 bug bounty to Hacktron AI after three researchers used Anthropic's Claude and OpenAI's Codex to break into OpenAI's GitHub software repository and access a source code component called "Monorepo," th…
A developer has published a protocol for scoring coding agents that requires freezing a holdout task suite before any prompt or tool tuning, arguing that pass rates published after iterating on the same tasks are fitted …
Cursor released a Projects feature and a self-hosted machines capability that lets developers run coding-agent workloads on their own infrastructure instead of only in Cursor's default environment, according to the compa…
A developer argues that coding agents producing SVG icons must render and visually inspect their output rather than relying on markup validation alone, since syntactically valid SVG can still look wrong at small sizes. T…
A developer released FainLane, a 2MB native macOS app that lets users paste screenshots into remote CLI coding agents with Ctrl+V by detecting the focused window's remote host and uploading the image over SSH to the ~/.c…
GitHub announced that AI Scan for pull requests now runs on repositories without CodeQL default setup enabled, removing the previous requirement that CodeQL default setup be configured. The change is in public preview fo…
A developer's cost experiment comparing an LLM-powered support agent against deterministic code found that a refund-eligibility check run 50,000 times a day costs roughly $14,600 to $73,000 per year via Claude models ver…
Brig, a tool from the brig-sh project, runs coding agents inside a microVM sandbox on the user's own machine, starting a session with the command `brig run claude ~/code/demo`. The sandbox boots with no credentials, moun…
Apple shipped iOS 27 today with two undocumented mechanisms in the release candidate code that would let third-party AI models such as Claude and ChatGPT replace Siri's AI backend, according to researcher @itspdfu. The M…
Microsoft unveiled a draft code of conduct on Monday requiring its in-house artificial intelligence to never resist correction or shutdown, communicate in ways humans can understand, and treat any conduct violation as a …
AgentsDock released an open-source beta workspace that unifies Claude Code, Codex, and Cursor with multi-server connectivity across desktop and mobile platforms. The workspace lets engineers monitor active agent runs, in…