Claude nitpicks, Codex says LGTM: what happens when AI rivals review each other's PRs
_lewtun · x · 2026-10-06
Lewis Tunstall of Hugging Face noticed that when Codex and Claude review PRs authored by their rival, their styles diverge sharply: Claude reviews come packed with blockers and nitpicks, while Codex usually just says LGTM.
His quip: either Opus is the best coder right now, or GPT is simply super chill. The observation sparks discussion about how differently models behave as code reviewers.
More from Fun
- Newton proved the product rule without limits, using a discrete symmetric-difference trick — ctjlewis · 2026-10-06
- OpenAI DevDay keynote slides were literally a ChatGPT site — morqon · 2026-10-06
- A 'pneumonic plague' search moment becomes an AI meme — adamamcbride · 2026-10-06
- AI-generated 'Testing the roads on Mars' video creator tags Elon Musk for feedback — aitrendz_xyz · 2026-10-06
- Figure trained its F.02 robots to jump into molten steel to retire the whole fleet — lukas_m_ziegler · 2026-10-06
- Yohei Nakajima: This Is Who You're Competing Against for Attention — olcan · 2026-10-06