Codex vs Claude: Coding Harnesses & Opus Degradation
May 12, 2026 · 559 messages · 81 active members
@samb69 argued Claude is bad for coding, running OpenCode with looping code+review agents (Opus 4.7 plan, GPT-5.5 code/audit). @sibunting reported Opus going dumb after an 11-day session with 17 compactions — builders sp…
Read full digest →