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.

Original post →

More from Models

Models channel →