A developer rebuilt PolyForge, a standalone Python CAD tool, from a ChatGPT skill into an offline package that renders parametric part templates to OpenSCAD, FreeCAD, or Blender without requiring an L…
Anthropic began invisibly watermarking text generated by its newest Claude models on August 2, 2026, with older models migrating over subsequent months, prompting a wave of subscription cancellations.…
The TeamPCP campaign in March 2026 used a stolen token to cascade across five ecosystems in eight days, publishing backdoored LiteLLM versions 1.82.7 and 1.82.8 on PyPI that swept LLM API keys, cloud …
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 rubbe…
A developer discovered that Claude Code subagents pinned to run on the cheaper Sonnet model were silently falling back to the session model, Fable, due to a frontmatter pin bug, causing unexpected cos…
Hermenics has released DeepSeek Code, an open-source CLI designed for working with DeepSeek AI models in the terminal. Inspired by Claude Code and OpenAI's Codex, the tool is available via npm and bun…
A new formulation for designing AI 'harnesses' classifies task topology by feedback density, search geometry, horizon, evaluation cost, and constraints, then chooses how explicitly search should be co…
Anthropic is developing collaborative projects for Claude Code that add Slack-like features, including persistent repositories as context, multiple threads within sessions, and shared memory across se…
A developer's essay argues that despite the rise of AI coding tools like Copilot, Cursor, and Claude Code, software engineering fundamentals remain essential. The piece contends that while AI accelera…
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 dev…
DeepSeek's V4 Flash model, launched July 31, topped AI leaderboards but completed only 53.8% of complex agent tasks in independent testing by Composio, with 129 of 240 runs passing across 30 multi-ste…
A developer released a ~60-line shell hook that blocks AI coding agents from running irreversible commands like `git reset --hard`, `rm -rf`, and `DROP TABLE`, exiting with code 2 and writing the reas…
A developer rebuilt the Cerebras knowledge base as an MCP server that exposes raw, LLM-free retrieval tools for external agents like Claude Code. The server makes zero model calls, instead handing rec…
LLM Wiki, a new open-source tool released as a plugin for Claude Code, OpenAI Codex, and OpenCode, enables parallel multi-agent research and session memory without hoarding transcripts, using human-ow…
The open-source project oh-my-claudecode (OMC), an orchestration layer for Claude Code and Codex CLI, reached 19,754 GitHub stars in one week, according to its repository. OMC runs a five-stage pipeli…
Lucid, a new output style for Claude Code, reduces jargon and rambling to make responses easier to understand in one pass, lowering the reader's cognitive load. The style keeps coding instructions int…
Developer Rehan30g built Conduit, a Python-based approval tool that lets AI coding agents request permission to run system commands via a popup dialog, eliminating the need to alt-tab to a terminal. T…
A new web tool lets Linux users inspect their machine's TPM event log entirely in the browser, using WebAssembly compiled from Google's go-eventlog library and built with Anthropic's Claude Code. The …
ProofRun, a new verification layer for AI coding agents, shifts trust from LLM-generated prose to actual local test execution by requiring agents to generate a cryptographic receipt via its CLI before…
A developer who built an autonomous Claude Code environment generating ¥1.2M a month has created a weekly automated curation system to combat 'skill rot' in Claude Code's auto-generated skills. The sy…