Fable and Opus both shift their priors when given more context, user says

dejavucoder · x · 2026-07-26

A user reports that both Fable and Opus will update their priors if you keep pushing them with more context and data, and even raise their expectations when told not to give up.

The comment was made in response to a claim that Opus 5 is less persistent than GPT-5.6.

Original post →

More from Models

Models channel →