Skip to content

Coding with AI

Assistants, editors, and how software actually gets written now.

12 of 27 stories
Tools

ReviewerAgent and StopContinue are community-developed packages designed to prevent coding agent premature stops and catch bugs using multi-model code review before git commits.

Why it matters: Using a secondary model to review commits can catch errors made by primary frontier coding agents before code enters version control.

  • Worth testing Test the open source tools in a local development environment to evaluate multi-model code review utility.
Hacker News — LLM · 6h ago
New Tech

OpenCode suffered a breach during a distillation attack, which exposed customer API keys. During the investigation, frontier AI safety guardrails blocked security teams from analyzing malicious code until specialized access was granted.

Google

Axios — Technology · 1d ago
Tools

An analysis of Claude Mods, plugins for Claude Code written in TypeScript or JavaScript that customize the behavior and appearance of the CLI and desktop interface.

Anthropic

Latent Space · 15h ago
Companies

Google

Mint — AI · 12h ago
Tools

Hacker News — AI agents · 1d ago
Use Cases

OpenAI

Simon Willison · 1d ago
Tools

GitHub

Hacker News — AI · 1d ago
Use Cases

GitHub

GitHub — AI & ML · 2d ago
New Tech

TechCrunch — AI · 2d ago
Tools

Hacker News — AI · 2d ago
Tools

Hacker News — LLM · 2d ago
Tools

Anthropic

Hacker News — LLM · 2d ago