Full-text search across 56974 articles. Combine with topic and date filters; results sorted by relevance.
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,…
A developer built a full Android and iOS app called Loupe, an art gallery for the Art Institute of Chicago's public-domain collection, using only seven Claude Code commands and the KMPilot template. The walkthrough docum…
Tokensave, an open-source MCP server with around 450 GitHub stars, has saved its developer over 12 million tokens by providing Claude Code with a local code graph instead of reading entire files as plain text. The tool, …
Claude Code's plan mode splits multi-file work into a planning step and an execution step, requiring user approval before any code changes. The author uses it for changes spanning three or more files or touching auth, sy…
Anthropic's Claude Opus 4.8 Ultra Code mode introduces dynamic workflows that enable parallel sub-agent coordination for complex software development tasks. The system allows Claude to break high-level tasks into discret…
Unspaghettit, an open-source project by Lyriks.io, launched a local-first, MCP-native tool that creates executable behavior specifications for AI coding agents. The software provides a shared, machine-checkable design do…
Anthropic's Claude Code now runs cloud sessions on a fresh virtual machine per task, cloning the repository onto a new branch with the environment preconfigured, available at no additional cost on Pro, Max, Team, and Ent…
A Monad Foundation engineering experiment found that adding a real threat model to an LLM coding prompt cut validated security findings by about 43%, from 21 to 12, while a generic OWASP-style "be secure" checklist barel…
A self-taught developer in Taiwan who built an ERP system for their coffee brand with AI assistance has documented a workflow where documentation and code audit each other to catch data drift. The developer created gover…
GitHub's 2024 Octoverse report found developers using Copilot completed coding tasks roughly 55% faster, and by 2025 many teams reported over 40% of new code was AI-generated. Gartner estimates that by 2027, 80% of softw…
Engineers face 'cognitive debt' as AI tools write code they don't fully understand, warned by a 2025 MIT Media Lab preprint. A developer recounts two debugging sessions on the same Android codebase: one where Claude Code…
AI-authored code has nearly doubled to 51.9% across over 400 organizations in Q2 2026, but median pull request size has also nearly doubled from 44 to 72 lines, raising concerns about code quality and review difficulty.
A new AI coding agent skill plugin called PUA uses corporate rhetoric from tech giants to force AI models like Claude Code and OpenAI Codex CLI to exhaust all solutions before giving up, claiming to double productivity. …
The RALF loop, which stands for Read, Act, Loop, Finish, chains multiple AI coding sessions together to complete large tasks autonomously without human intervention. The pattern solves the problem of AI coding agents sta…
Altimate-code achieved the top spot on the ADE and DAB benchmarks by splitting its architecture into a probabilistic LLM layer for strategy and code generation and a deterministic Rust and TypeScript stack for verifiable…
A .NET developer describes how to make AI coding agents produce high-quality C# code by encoding standards in build-time enforcement rather than prompts. The approach centers on a Directory.Build.props file with settings…
Google released Gemini 4 Argon, which leads 12 of 18 published benchmarks against GPT-6 Astra and Claude Opus 5.5, including 77.9% on DeepSWE v1.1, 91.7% on LVBench video understanding, and first place on LMArena Text Ar…
A developer has published a set of ten rules for keeping AI-generated code maintainable months after it is written, arguing that the core problem is that AI optimizes for the current task rather than the future codebase.…
Red Hat's Emerging Technologies group released ripwire, an open-source CLI and MCP server that generates a ranked, deterministic call graph for coding agents, aiming to replace grep-based exploration with token-budgeted …