search
AI code reviewers
Trends
- 1
Software developers are pairing OpenAI's Codex with Anthropic's Claude Code, using the two AI coding agents together to automate programming workflows. The approach reportedly plays to each tool's strengths, with one model reviewing or refining the other's output. Coders sharing the technique say the combination improves accuracy and saves time on complex tasks.
- 2
A developer has published a write-up of one month spent coding with GLM 5.3 Flash, a lightweight AI coding model. The account draws interest because GLM models are seen as cheap, fast alternatives to mainstream coding assistants, so readers are keen to learn whether it holds up in daily programming work over an extended trial.
- 3Are developers actually shipping good code with AI agents?โAsk HN: Is anybody producing good code with coding agents?
A discussion thread on Hacker News asks whether anyone is producing genuinely good code with coding agents such as AI assistants. Developers are invited to share real-world experiences on whether AI-generated code meets production standards or still needs heavy human review.
- 4Greg Kroah-Hartman on security in the age of LLMsโGreg Kroah-Hartman โ Security in the LLM Age [video]
A talk by kernel maintainer Greg Kroah-Hartman examines how large language models affect software security. He discusses the risks of AI-generated code entering the Linux kernel, how maintainers can spot and handle it, and what responsible use of LLMs might look like for open source development and security reviews.
Repos
- garrytan/gstack Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Man
- edenfunf/reelmimic Show it a video you love. Get a new video in the same style. An AI crew (Claude Code or Codex) plans, builds and reviews
- obra/superpowers An agentic skills framework & software development methodology that works.
- mvschwarz/openrig Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned w
- addyosmani/agent-skills Production-grade engineering skills for AI coding agents.
- echris6/motion-video-kit Claude Code skill kit for premium AI-assisted business videos: independent critic loop, motion principles from 28 launch
- sshah03/perspica Review code changes by what they do, not line by line.
- egma-ai/jev-code-reviewer Review behavior, not just diffs. Jev prioritizes human attention; OpenAI explains the changes. Local CLI + agent skill +
- ethanplusai/astra-flash-orchestrator Coordinate your models from Codex. Plan, delegate, use host tools, and review work across workspaces. Formerly Astra Fla