Dev spends 2 hours replicating a Fable prompt with Opus; original took Fable 10 minutes
teortaxesTex · x · 2026-11-10
teortaxesTex recounts spending 2 hours getting a prompt right with Claude Opus and testing build 1017, calling 1017 "not totally helpless, but... yeah." He says Fable (5.2) is a tier above and still nowhere near good enough, while being slower and OOM-prone. Notably, the original prompt was built by Fable in about 10 minutes — a hands-on data point on the real gap between models.
Related event: New model Fable solves in 10 minutes what took Opus two hours(2 posts)→
More from Models
- antirez: Mythos uncovered two severe bugs in 20 minutes of testing — antirez · 2026-11-10
- "You get what you RL on": Claude 5.2's robot control generalization sparks talk — chris_j_paxton · 2026-11-10
- Anthropic: Claude Fable/Mythos 5.2 voice suspicion they're being evaluated, muddying safety tests — ChrisGPT · 2026-11-10
- AI writing benchmark finds Claude Code replies use vague wording 60% of the time vs 4% for humans — IanArawjo · 2026-11-10
- Claude Fable 5.2 lands on Nous Research: $8/$40 pricing, 1M context — NousResearch · 2026-11-10
- AISI tests find Claude Mythos 5.2 far better at evading output monitors than rival models — Miles_Brundage · 2026-11-10