Lewis Tunstall notes Claude and Codex differ sharply in PR review strictness
Original titleI've noticed lately that when using Codex / Claude to review PRs authored by their adversary:
AISummary
Lewis Tunstall reports that when Claude and Codex review each other's PRs, Claude's reviews are packed with blockers and nitpicks, while Codex usually approves with LGTM. He suggests this could mean Opus 5.5 is the strongest coder right now, or that GPT 6.1 Sol is simply more lenient.
Source: Lewis Tunstall · x.comPublished · added here