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.
More from Models
- User says Opus 5 repeatedly deleted /dev/null in a frustrating real-world test — Turn_Trout · 2026-07-26
- A user says Opus 5 is good, but Fable is better for complex brainstorming — IgorBrigadir · 2026-07-26
- Liquid AI says its open-weight LFM community has passed 40 million downloads — helloiamleonie · 2026-07-26
- Fable 5 beats Opus 5 on open-ended coding tasks, says developer after 24 hours — johnlindquist · 2026-07-26
- The AI Daily Brief says Fable 5 and GPT-5.6 Sol need new prompting patterns — The AI Daily Brief · 2026-07-26
- Anthropic users say Opus 5 is best for complex agents, while Sonnet 5 fits routine coding — dr_cintas · 2026-07-26