Blogger: Fable nailed in 10 min a prompt that took Opus 2 hours of tuning
teortaxesTex · x · 2026-11-10
User teortaxesTex shared a hands-on prompt-tuning comparison: a task that took him 2 hours to get right with Opus (testing build 1017) was completed by Fable's core model in 10 minutes. He called Opus "not totally helpless, but... yeah," and said Sol is a tier above Opus yet still nowhere close — and slower, with OOM issues. He added that despite having many tools available, he believes Fable would have managed without them.
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