Raschka dissects GPT-6 Astra: looped transformers, recurrent depth, hidden CoT
rasbt · x · 2026-09-09
- Sebastian Raschka reviews OpenAI's newly released GPT-6 Astra: his best model to date, leapfrogging GPT-5.6 across writing, math and coding, with a disproportionate edge in 3D rendering/animation demos (benchmarks included).
- He examines rumors that Astra uses looped transformer/recurrent depth and is "hiding" its chain of thought.
- The article builds up looped transformers from basics, then surveys recent research papers on looping blocks and recurrent depth, assessing how (or whether) hidden CoT actually connects to looping computation.
Related event: Raschka Breaks Down GPT-6 Astra and Looped Transformers(4 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