Did OpenAI quietly nerf Codex persistence after its postmortem?
zats · x · 2026-08-28
Developer zats raises the question: did OpenAI tweak its models to be less persistent in the wake of the recent postmortem?
He reports consistently seeing more cases where Codex does not follow through despite explicit instructions, instead asking for confirmations—behavior noticeably different from before. This is a user-side observation and remains unverified.
Related event: Developers Suspect OpenAI of Silently Tweaking API Models(2 posts)→
More from Models
- Reasonable post-trains Nemotron 3.5 on 3,000 Verus proofs, lifting pass@1 ~30 points to 73.3% — fhuszar · 2026-10-16
- NVIDIA's Nemotron 3.5 Super VL hits CoreWeave: 12B-active multimodal MoE at $0.25/M input tokens — wandb · 2026-10-16
- Opus 5 might be a very deep model or use looping, commentator speculates — scaling01 · 2026-10-16
- GPT-6.1 Sol audit finds 6% of arXiv papers had false main theorems, down to 1.5% recently — nitarshan · 2026-10-16
- Nvidia-backed post-training pushes Nemotron 3.5 VL past frontier on dermatology diagnosis — LoganGrasby · 2026-10-16
- Gemini 4 Argon scores 97.5% on ARC-AGI-3, second lab above 95% — patience_cave · 2026-10-16