Raschka deep-dive: GPT-6 Astra, looped transformers, and the hidden chain-of-thought question
AxSaucedo · x · 2026-09-15
Sebastian Raschka published a long-form analysis of OpenAI's new GPT-6 Astra and the research behind looped transformers.
- Hands-on impressions: He calls Astra the best model he has used so far, leapfrogging GPT-5.6 across writing, math, and coding, and disproportionately strong at 3D rendering and animation demos.
- Core topic: A detailed explainer of looped transformers — reusing the same transformer blocks over multiple iterations to create implicit recurrent depth and hidden internal reasoning chains.
- Hidden CoT: He examines rumors that Astra "hides" its reasoning trace, how that relates to recurrent-depth architectures, and highlights new insights from recent research papers on the topic.
Related event: Raschka Deep-Dives GPT-6 Astra's Looped Transformer Architecture(2 posts)→
More from Models
- Coverage tests across 3 runs: DeepSeek V4.1 Flash 21.7→33, GLM-5.3 Flash 17.7→24 — PawelHuryn · 2026-09-15
- ChatGPT Plus vs Business: heavy users compare real-world Sol High usage limits — geler1 · 2026-09-15
- Tinfoil: Open-source safety classifiers are scarce, frontier labs urged to release more — yuntiandeng · 2026-09-15
- Depending on a single AI vendor is riskier than open models, argues researcher — xeophon · 2026-09-15
- Grok 5 Roadmap, Gemini 4.0 Pro 'Argon' Leaks, and Claude Opus 5.2 Preview Roundup — WorldofAI · 2026-09-15
- User verdict after testing small models: DeepSeek v4.1 Flash is the minimum viable model for real work — solyarisoftware · 2026-09-15