Hypothesis: Astra's 3D modeling leap comes from strong no-CoT abilities
a_karvonen · x · 2026-09-07
akarvonen hypothesizes that Astra's big jump on 3D modeling stems from its strong no-CoT capabilities.
He has long thought that reasoning in English tokens is a major limitation for spatial reasoning. He notes an alternative explanation: it could simply be better targeted RL environments.
Related event: Debate Over Astra's 3D Leap: No-CoT Ability or Scale?(3 posts)→
More from Models
- Kimi K3.1 Pro regresses on Debate Benchmark while DeepSeek 1017 gains at lower cost — teortaxesTex · 2026-10-27
- 4 Hours of LLM Startup Research Produced a Convincing but Nonsense Product Thesis — annetgriffin · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- MiniMax matches Claude Opus 4.5 in non-benchmaxxed evals, users report — teortaxesTex · 2026-10-27
- Real-world math: GPT-6.1 Terra's half price is offset by 2-3x token usage, costing more than Sol — lordpuddingcup · 2026-10-27
- Fable 5.5 rumored to ship this week as partners still test — kimmonismus · 2026-10-27