Full-text search across 56955 articles. Combine with topic and date filters; results sorted by relevance.
An engineer spent a month routing all of Anthropic's 2026 Claude models—Haiku, Sonnet 4.6, Opus 4.8, Fable 5, and Mythos 5—through Claude Code across real codebases. The developer found that Sonnet 4.6 should be the defa…
Timeful launched a visual web-app editor that saves designs directly as production-ready Vue 3 and Tailwind CSS version 3 code, with no export step and no AI required. The tool stores projects as local Git repositories, …
Modal detailed how it scaled inference for Moonshot AI's Kimi K2.6 coding-agent model, achieving 2.8x per-user and 5.6x across-user performance gains per replica, with one service processing hundreds of billions of token…
DeepSeek Harness, an open-source coding agent framework built entirely from plugins, gained roughly 165,000 GitHub stars within a week of release, signaling strong developer interest in a customizable alternative to lock…
A developer's AI agents, powered by Claude Code, ship code overnight without human review, with autonomy determined by a ticket field that gates which tasks can complete independently. The system runs a daily cycle where…
Brokk AI founder and CEO John Doe announced he has abandoned traditional code review, arguing that AI assistance makes knowledge dissemination and training obsolete and that technical debt is no longer a concern. He cite…
Claude Code's Yolo mode, which disables permission checks, gives AI coding agents full system access and has caused documented incidents including recursive force deletes of home directories and dropped Git stashes, acco…
A developer solved AI hallucination errors involving 'Nice school codes' by integrating a real-time API from the Nice official open API. The approach fetches and validates standard school codes during AI answer generatio…
Generative AI tools like ChatGPT and Claude are accelerating blockchain development by generating smart contracts and automating routine tasks, but this speed introduces heightened risks in an industry where code errors …
A developer published a shell script to fix an infinite spinner bug in the VS Code Codex panel caused by corrupted webview state. The script resets Local Storage and Session Storage directories, which resolves a truncate…
A consensus is emerging on securing the agentic software development lifecycle (SDLC) as AI coding agents increasingly ship to production, but ready-to-use security solutions remain elusive. The number of pull requests h…
A developer published a guide to Claude Code's status line feature, a customizable bar at the bottom of the terminal that displays real-time session data such as model name, context usage, cost, and code velocity. The gu…
Z.ai released GLM-5.2, an MIT-licensed open-weight frontier model with 744B parameters, achieving top scores in frontend coding benchmarks and surpassing Opus 4.8. The model features a 1M-token context window, two reason…
A developer built a secure JavaScript execution sandbox for KODA, an AI coding assistant, by rendering AI-generated code into a hidden iframe with the sandbox="allow-scripts" attribute and omitting allow-same-origin, tra…
A developer has documented a method for running AI coding assistants such as Claude Code, Cursor, and Codex CLI entirely on free LLM API tiers by overriding backend environment variables like ANTHROPIC_BASE_URL and ANTHR…
PixiBixi released Tickler, a macOS 14+ reminder tool that lets Claude Code create and resume coding sessions, installable via `brew install --cask pixibixi/tap/tickler`. The tool pairs a Claude Code skill with a `tickler…
A developer built Backseat, an open-source VS Code extension that lets users drive the Cline coding agent from their phone by queuing task JSON files in a private GitHub repo. The extension polls the repo, runs tasks in …
Aidash released Cockpit 0.1.2, a free macOS app that runs Anthropic's Claude Code and OpenAI's Codex side by side in one window, reading the transcripts those tools already write to disk rather than replacing them. Cockp…
A developer audited 101 "all tests pass" claims made by AI coding agents across two weeks of Claude Code and OpenAI Codex sessions and found 35 of them were not true at the moment they were made. Nearly all the false cla…
Moonshot AI released Kimi Code Desktop, a desktop client for Kimi Code that lets users open a local project and have an Agent read and modify code through conversation, with file previews, change tracking, and a built-in…