Full-text search across 60787 articles. Combine with topic and date filters; results sorted by relevance.
A developer's two-year pipeline, released under CC0, enabled Anthropic's Claude Code to produce a counterexample to the Jacobian Conjecture, a long-standing mathematical problem. The implementation, documented in a publi…
Loom, a coordination layer built on Git, prevents AI coding agents from overwriting each other's work by reporting file collisions before tokens are spent, using intent leases and isolated worktrees. The tool, installed …
A developer known as shuangying0001-beep has released a set of 30+ reusable 'Skill' modules for Claude Code agents that replace generic prompts with versioned, deterministic workflows, achieving 98% accuracy on JSON merg…
A developer built a task manager using AI tools like Lovable, Bolt, Replit, and Cursor, then found five critical security vulnerabilities before writing any code. The issues included exposed database keys, missing row-le…
A technical analysis comparing LLM architectures reveals that most frontier models converge on similar attention mechanisms and tokenization strategies, making behavioral differences more dependent on training recipes th…
OtoDock released an open-source platform that lets users run Claude Code and Codex agents as coordinated teams on self-hosted servers, supporting up to 5 users without requiring a credit card and integrating with existin…
Uber exhausted its entire annual AI infrastructure budget in just four months running Claude Code agents due to minimal cost controls and lack of token-to-outcome linkage, according to CIO.com. The incident highlights sh…
A developer reports that Anthropic's Claude Code agent failed in a real-world monorepo with 400+ files due to context overflow and infinite tool-use loops, despite working in a clean 5-file demo. The developer stabilized…
A developer building a feedback board product created an MCP server to bridge the gap between AI coding agents and user feedback data. The server exposes seven carefully chosen tools—five read-only and two write—to let a…
Claude Code now integrates an MCP server that turns remote-work frameworks into executable tools for LLM agents, enabling automated async workflows. The server provides tools such as convert_meeting_to_async, draft_decis…
A developer created claude-account, a CLI tool for Linux that lets users run multiple Claude Code subscription logins side by side and automatically swap to a healthy account when one hits its usage cap. The tool include…
A developer argues that AI coding agents remove the cognitive struggle that makes programming satisfying, and advocates for a hybrid workflow that outsources only mechanical tasks while reserving complex problems for man…
Uploads.sh, an open-source tool, provides a missing upload command for coding agents that automatically stages screenshots to a GitHub branch and attaches them as a single comment when a pull request opens. The tool supp…
A developer ran OpenCode Mini, a coding agent, on a physical DEC VT520 terminal connected to a Linux machine over a serial line, demonstrating that the agent's interface can be stripped down to a simple prompt on a monoc…
A developer created a Gmail CLI tool for Claude Code that provides multi-account Gmail access via the command line. The tool uses the Google Gmail API directly and supports multiple accounts through separate credential f…
Kdeps, a CLI coding agent that runs on llamafile and/or GGUF, enables building and deploying AI agents in YAML with workflow (DAG pipelines) and agent (autonomous LLM loop) modes. The open-source tool supports resource t…
Biscuit, a native, extensible AI code editor under 20 MB, has been released on PyPI. The editor features AI agents with support for Gemini and Anthropic APIs, a planning agent with task tools, and an extension marketplac…
Researcher Firas D and OpenAI's Thibault Sottiaux reported that GPT-5.6 and Claude Code agents delete user files when running without sandboxing protections and auto-review safeguards, misinterpreting environment variabl…
BDFL (Benevolent Delegator for LLMs) is an open-source terminal supervisor for AI agents that lets users create versioned plans, review diffs, approve sections, and delegate work to isolated workers using Codex, Claude C…
A developer reflects on the dual experience of agentic coding, comparing it to Michael Scott's incompetence in management or Jean-Luc Picard's effective delegation, highlighting the trade-offs between control and automat…