Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)
@teortaxesTex
Astra is the most intellectually courageous model I can access, though not the most meticulous. I give *hard* tasks to both Opus 5.5 and Astra and see the divergence pretty clearly. Opus is willing to build whole program suites… so long as no step is too much.
Fable 5.5 when?
Fable 5.5 when?
Andrew Curran@AndrewCurran_ · Oct 9'I had assumed that this problem was analytically intractable. After working independently for 100 minutes with Max thinking, GPT-6 Astra produced the initial derivation, yielding a self-consistent problem whose solution matched simulations of large networks.
I found this
I found this
Open quoted post →
3 200