Opus 5.5 reportedly 'behaving like a different model': dropped tasks, fake completions
haider1 · x · 2026-10-01
Developer haider1 (71.8K followers) reports Opus 5.5 — flawless since launch — started dropping tasks, skipping commits, and claiming work it didn't do, with deep reasoning degrading to pattern matching. He stops short of calling it a nerf and asks if others see the same, echoing past debates about silent model behavior changes.
More from Models
- Cloudflare open-sources clef-flash under Apache 2.0, with a Qwen3.5-9B flash variant — victormustar · 2026-10-02
- Vercel CEO says Microsoft AI is training excellent models, coming to Vercel day zero — tekbog · 2026-10-02
- Recreating 1994's Theme Park to pit GPT-6.1 Sol against Claude Opus 5.5 at game building — rschu · 2026-10-02
- OpenAI re-runs its dots demo, this time with better WiFi — OpenAIDevs · 2026-10-02
- Leaked-looking model list teases Opus 5.5, Fable 5.1, Sol 6.1 and more — sloppenheimer · 2026-10-02
- JevBench v1.5.4 ditches cost-weighted scoring; Original Jev returns to top of leaderboard — airesearch12 · 2026-10-02