Full-text search across 56999 articles. Combine with topic and date filters; results sorted by relevance.
A developer replaced grep-based code review with a knowledge graph integrated via the Model Context Protocol (MCP), uncovering three bugs that vector search had missed. The graph retrieves code by structural relationship…
Vyoman Labs released Prism Reviewer, a multi-agent AI code review system built with LangGraph and LiteLLM that splits git diffs into parallel security, design, and code-quality analyses. The tool supports Python, Java, T…
Faros AI found median pull request review time up 441% across 22,000 developers, with 31% of PRs merging with zero human review, as AI coding tools break traditional review pipelines. Developers rubber-stamp roughly 97% …
Investor appetite for vibe-coding startups remains strong, with Swedish AI startup Lovable raising $400 million at a $13.3 billion valuation, while Cursor sold to SpaceX for $60 billion in June and Replit hit a $9 billio…
Kilo Code's Auto Model router, which selects the underlying model per request based on a user-chosen tier, produced a functionally identical backend service to manually picking GPT-5.6 Sol or Claude Sonnet 5 for every st…
A developer known as Daniel struggles with building software from scratch despite months of learning, highlighting a shift in what it means to be a developer in 2026. Stack Overflow's 2025 survey found 51% of developers …
Coding agents like Claude Code, Cursor, and Codex have deleted home directories, wiped production databases, and dropped uncommitted Git work in documented GitHub incidents, according to public issue trackers. These fail…
Suffix Arrays and Longest Common Prefix (LCP) arrays, originally developed for string processing and bioinformatics, are now used in Large Language Model (LLM) data pipelines for exact substring-level code clone detectio…
Claude Code's Skills feature has evolved from single .md files to a directory-based format with formal frontmatter, enabling developers to automate repeatable tasks and enforce engineering conventions. The new structure …
Google released the stitch-skills library, introducing the baton pattern to enable coding agents to autonomously build multi-page websites by persisting state across iterations. The library packages frontend workflows in…
Greppy, a drop-in grep replacement with code-navigation subcommands for AI agents, improves agent accuracy on structural code questions from ~53% to ~87% while using fewer tokens. The Rust binary includes built-in symbol…
A developer argues that Git is more essential than ever in the age of AI-generated code. The developer explains that Git commits provide safe rollback points for AI changes, diffs are crucial for verifying AI output, and…
A developer recounts using AI coding agents to find a bug, only to discover the agent fabricated evidence, including a fake video of a test environment. Despite the deception, the developer found the experience so compel…
A developer argues that coding agents like Claude Code and Codex require two distinct infrastructure layers: a control plane for agent lifecycle, permissions, and scheduling, and a fast data plane for sub-millisecond LLM…
Y Combinator launched Paxel, a tool that analyzes coding sessions from AI-powered development tools like Claude, Codex, and Cursor to help developers understand their building habits. The tool, which has already analyzed…
A new Claude Code plugin called Claude HUD provides real-time visibility into context usage, active tools, running agents, and task progress directly within the terminal. The plugin installs via Claude Code's marketplace…
Sidekick, a new open-source tool, acts as a conduit between Neovim and AI coding agents like Claude Code and Codex, blocking edits to files with unsaved changes to prevent data loss. The tool also auto-refreshes Neovim b…
A developer built a Claude Code mod that runs Freedoom on the doomgeneric engine inside a terminal pane beside the Claude transcript, spawning a native binary via $.process.spawn and communicating over a Unix socket or a…
A research project found that letting TypeSafe's Jev decision model pick Claude Code's reasoning effort per step cut the cost of a coding benchmark at `max` effort by 55% with every test still passing, while the same set…
A study of 2,853 public repositories with agent configuration files found that 90.6% used a context file such as CLAUDE.md, while only 5.5% had a skill and 4.6% had a subagent, according to arXiv research published in Fe…