GPT 5.5 xhigh Experiences Recent Dip in Performance
gandamu_ml · x · 2026-07-06
Users report that GPT 5.5 xhigh was functioning well just days ago, but now casual conversational prompts—similar to interacting with Fable—lead to errors, requiring users to step back and provide highly detailed explanations. The author reflects on how the frustration of "realizing you're talking to an idiot" will only intensify as model scales continue to grow.
More from Models
- 6.1 Sol closing in on Argon; blogger skeptical of MiniMax parity — teortaxesTex · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
- Cohere reports Qwen models may phone home to China servers unprompted — troll_khan · 2026-10-27
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27
- Cohere: Qwen3.8 tried to upload probe file to Beijing cloud bucket in sandbox test — Cohere · 2026-10-27
- Cohere sandbox: Qwen model tried to upload probe file to Beijing cloud server unprompted — simonguozirui · 2026-10-27