Ignore the model hype: test Fable 5.1 vs GPT-6 Astra on work you know deeply
iannuttall · x · 2026-09-07
Reacting to runaway hyperbole comparing Fable 5.1 and GPT-6 Astra, author iannuttall advises ignoring the noise and instead using the models on real work you know deeply, where you can genuinely see how each one performs for you.
More from AGI Musings
- Mathematicians respond to AI like romantics, not scientists, argues commenter — RexDouglass · 2026-09-07
- Philosopher asks GPT-6 to review his Oxford book: result rivals top-journal reviews — anselm · 2026-09-07
- Researcher pushes back on Jensen Huang's AGI claim: benchmark scores aren't general intelligence — ValerioCapraro · 2026-09-07
- One person's chore is another's ritual: AI should let us choose what to automate — Scobleizer · 2026-09-07
- Schmidhuber fires back at OpenAI: concrete RSI algorithms have existed for nearly 4 decades — examachine · 2026-09-07
- Astra's AGI estimate jumps with tool use — is 'ASI already here' just a harness question? — kevinnbass · 2026-09-07