Full-text search across 62671 articles. Combine with topic and date filters; results sorted by relevance.
A Hacker News user reports their company has shifted to a six-week implementation cycle with one-week planning/retro, where standups focus on demos and AI agents generate Product Requirement and System Design documents f…
The IRCv3 Working Group began adding AI markers to software listed on ircv3.net when known to be developed with substantial AI assistance, and Codeberg e. V. members voted 358 to 144 to prohibit vibe-coded projects from …
Chinese AI startup DeepSeek launched V4 Flash, an open-weight code-generation model under the MIT License, priced at approximately 28 cents for coding output that costs $25 on Anthropic's Claude Opus 4.8, making it rough…
Wienerdog, an open-source tool under MIT license, provides persistent memory and self-improving skills for AI coding agents Claude Code and Codex, requiring only an existing Anthropic or OpenAI subscription. The tool, in…
Anthropic CEO Dario Amodei and senior leaders signed a petition asking the U.S. government to support international tools for pacing automated AI development, citing evidence that its Claude model is accelerating AI rese…
Developer Prabhu Avula released Scout, an MIT-licensed tool that ingests an OpenAPI spec and documentation to build a grounded understanding of any enterprise platform, including architecture, entities, workflows, starte…
Cursor, Bolt, Lovable, and GitHub Copilot AI coding assistants frequently generate CORS middleware that reflects the incoming Origin header with credentials enabled, creating a critical vulnerability (CWE-942) that allow…
Anthropic's Claude Opus 5, its newest Opus model designed for complex, multi-step coding tasks, is now available in GitHub Copilot for Copilot Pro+, Max, Business, and Enterprise users across multiple IDEs and platforms.…
In part 9 of a series on building AI agents in Rust, the author introduces sandboxed code execution, allowing the agent to run arbitrary shell or Python code on the user's machine. The post emphasizes the power and dange…
H5i-Python, a Python SDK for the h5i orchestra engine, enables programmable multi-agent orchestration across coding agents like Claude Code and Codex. The SDK lets developers define and execute reproducible multi-agent c…
A developer rebuilt their agentic coding kit, Agentic Coding Kit v6, to eliminate wasteful process loops that made small tasks expensive. The new version enforces a leaner rule where the main coding session owns the outc…
Researchers at ASSET Research Group published a proof-of-concept attack called GhostCommit that exploits coding-agent pipelines by hiding exfiltration instructions inside image files in pull requests. The attack embeds a…
Boris Cherny, head of Claude Code, advocates replacing manual prompting with agent loops that automate coding tasks. Bun's team used such loops to rewrite 750,000 lines of code in 11 days with 99.8% test pass rate, and S…
Marc, founder of ClaimMate AI, is building an AI software engineering platform that helps developers generate code, explain existing code, debug issues, create tests, review code, and build applications from simple promp…
Mistral AI released Leanstral 1.5, an open-source code agent model for Lean 4 formal proof engineering, available under Apache-2.0 license. The 119B-parameter model achieves state-of-the-art results on formal reasoning b…
SelectPdf has released a free, open-source (MIT) set of Agent Skills called SelectPdf AI Tools that prevents AI coding assistants from hallucinating PDF API methods. The tools provide accurate, version-matched knowledge …
A developer built 25 executable skills for AI coding agents, packaged into a single open-source repository compatible with Claude Code, Codex, Cursor, and Hermes Agent. The skills include debugging, planning, code review…
A former software company founder reports that at a friend's 15-person firm, developers rely heavily on AI tools like Claude, with code no longer serving as the source of truth, code reviews done by AI, and multiple simu…
Microsoft released an open-source dependency manager for AI agents called Agent Package Manager (APM), which allows developers to declare agentic dependencies in a manifest file and reproduce them across different coding…
A developer built figma-connect, a local tool that lets AI agents verify their UI code against Figma designs using pixel-perfect comparison. The tool renders code in headless Chromium, exports the matching Figma node, an…