Claude Fable 5 Max Also Misjudges Time Spent

goodside · x · 2026-07-14

The author adds that he put ChatGPT first because it displays response times in the UI; however, **Claude Fable 5 Max** suffers from a similar issue. On the same prompt, it also spent less than 2 minutes thinking; more interestingly, it later "self-admitted" that it didn't actually think for an hour. This further supports the previous observation: LLMs are unreliable at estimating their own thinking time.

Related event: LLMs Lack Accurate Intuition About Their Own Thinking Time(2 posts)→

Original post →

More from Models

Models channel →