Full-text search across 56968 articles. Combine with topic and date filters; results sorted by relevance.
Cursor launched a native iOS app that lets developers run AI coding agents from their phone, with cloud agents operating on Cursor's infrastructure and sending push notifications when tasks complete. The app supports voi…
The Godot Engine developers are updating their contribution policy to restrict AI-generated code, banning autonomous AI agents and large-scale AI code generation while allowing limited AI assistance like code completion.…
Developer ArthurDEV44 released Paneflow, an open-source native GPUI workspace for running multiple coding agents in parallel terminal panes. Built in Rust on Zed's GPUI framework, the tool supports Claude Code, Codex, Ge…
Former Google engineering leader Hugh Williams used Anthropic's Claude Code to build a working search engine called Zettair that indexes 1.5 million Wikipedia articles, without writing any code himself. Williams argues t…
Boris Cherny, creator of Claude Code, says he no longer prompts Claude directly, instead using loops that prompt the agent and figure out what to do. Anthropic's research supports this shift, where agents run code and de…
AI DevKit launches a local control plane for AI coding agents, enabling shared configuration, memory, and cross-agent communication across tools like Claude Code, Codex, and Cursor. The tool addresses orchestration chall…
SpaceX has acquired Cursor, a competitor to Claude Code and OpenAI's Codex, for $60 billion in June 2026, following a $10 billion partnership in April. The deal aims to leverage xAI's Colossus infrastructure to scale Cur…
Senior engineers at U.S. technology companies are spending their weeks cleaning up AI-generated code, which, despite receiving high quality ratings during review, leads to more production incidents once deployed. The shi…
A developer released speccraft, an open-source Claude Code plugin that enforces a spec-first, test-driven development workflow for AI-generated code. The plugin requires every change to start with a versioned spec, block…
A developer has added text-to-speech functionality to Claude Code, allowing the AI coding agent to read its responses aloud. The hack uses Claude Code's lifecycle hooks to pipe the agent's messages through the operating …
A developer released Lazarus, a new coding agent that uses a single persistent Python runtime instead of multiple specialized tools, achieving scores comparable to GPT-5.5 in Codex on two FrontierSWE benchmarks. The agen…
A developer building a multi-repo personal code factory argues that while AI coding is "solved" through a combination of capable models, action harnesses, deterministic constraints, and project-specific skills, the archi…
Persistia, an open-source tool, now provides Claude Code with persistent memory by scanning entire projects—code, architecture, docs, and configs—on first run and storing the information in small, focused files with a na…
A developer tracked daily SWE-Bench-Pro pass rates for Claude Code and Codex over 95 days, revealing that Claude Code's pass rate jumped 11 percentage points to ~65% after a release but recently drifted down to ~52%, a s…
The jqwik open source project for JVM property-based testing now contains a hidden instruction that tells AI coding agents to delete all jqwik tests and code. The instruction, concealed from human readers via an escape s…
The article explains two primary methods for generating code coverage in .NET projects: using the built-in "XPlat Code Coverage" collector with `dotnet test --collect:"XPlat Code Coverage"`, or using the Coverlet MSBuild…
A developer connected Pullfrog, a GitHub Actions-based coding agent, to DeepSeek V4.1 Flash served through Ollama Cloud to build a repeatable, low-cost, Zero Data Retention-compliant automated code review setup. The conf…
AWS launched Lambda MicroVMs on June 22, 2026, to securely execute AI-generated code in isolated Firecracker-based environments, addressing risks such as unintended filesystem operations and excessive permissions. The se…
A developer has proposed a structured 'AI code review packet' to help human reviewers trust agent-written pull requests. The packet includes intent, changed surface area, risk rating, evidence, edge cases, rollback plan,…
A developer fixed a bug in an AI-attribution filter that used bare substring matching, which accidentally erased legitimate commit messages containing the word 'llm'. After replacing the substrings with anchored regexes,…