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)→
More from Models
- Frontier models improve on earnings-direction benchmarks, but open models still lag — dougclinton · 2026-07-21
- Holo-3.1-35B-A3B-NVFP4 has topped Spark Arena’s 2-node board for weeks — Porespellar · 2026-07-21
- GPT-5.6 Sol is judged better than Opus 4.8 at disagreeing without sounding smug — JeremyNguyenPhD · 2026-07-21
- Claude Opus 4.8 Fast felt wildly overpriced in one coding session, user says — immersive-matthew · 2026-07-21
- Microsoft Research shrinks pathology models 50%+ and keeps 97% of GigaPath performance — iScienceLuvr · 2026-07-21
- Cheap Chinese open-weight models are pressuring OpenAI and Anthropic’s economics — kimmonismus · 2026-07-21