Neel Nanda replicates Astra system card: no-CoT reasoning jumps 1.75x over next-best models
NeelNanda5 · x · 2026-09-11
Neel Nanda replicated the Astra system card's claim of doing substantial computation without chain of thought: Astra takes 1.75x the steps of the next-best models (Fable 5.1/Gemini 3.8 Flash) with no CoT, and no-CoT capabilities improved far more than with-CoT ones.
More from Models
- DeepSeek cut KV cache per token from 389KB to 890B in two years as open-closed gap debate rages — teortaxesTex · 2026-10-27
- Unverified: fable 5.5 speculated at 4-5T parameters to outscale 1-3T Opus — haider1 · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27