I've noticed lately that when using Codex / Claude to review PRs authored by their adversary: - Claude reviews are packed with tons of blockers and nitpicks - Codex is usually LGTM 👍 So either Opus…
Original titleI've noticed lately that when using Codex / Claude to review PRs authored by their adversary:
AISummary
…5.5 is the best coder right now or GPT 6.1 Sol is just super chill
Source: Lewis Tunstall · x.com