Researcher flags severe LLM degradation as a mission-critical concern

doodlestein · x · 2026-09-20

AI researcher doodlestein shared a case of severe LLM performance degradation (the model later attributed it to a 'severe processing error'). He argues this kind of behavior is extremely important to understand if LLMs are to be used in mission-critical settings, noting he has never seen that level of degradation in Claude or ChatGPT.

Related event: Gemini Flash 3.8 Glitches Badly on Routine Prompt, Raising Reliability Concerns(4 posts)→

Original post →

More from Models

Models channel →