OpenAI's flagship uses looped transformers for math and coding but still needs alignment work
The Decoder · rss · 2026-10-15
The Decoder reports OpenAI is racing to finish its next flagship model, which uses the same looped transformer technique as Astra to boost math and coding performance — at the cost of making safety monitoring harder. Microsoft accidentally revealed details of how the technique works on a public page. Employees say one or two new models will likely ship by year's end even if the flagship isn't ready, as it still needs alignment work.
More from Models
- Opus 5.5 still leads a month later, but open-weight decision models are closing in — airesearch12 · 2026-10-16
- Google restricts Gemini Pro access for Google Plus subscribers, matching free tier — EmergencyLess8861 · 2026-10-16
- Meta releases Muse Spark Open, trained with vLLM-powered RL inference from day one — colinmcnamara · 2026-10-16
- Meta open-sources Muse Spark: runs on two Mac Studios, license bans passing output off as human-written — mawcopolow · 2026-10-16
- Golden Gate Claude explainer resurfaces: interpretability premise still holds — HarperSCarroll · 2026-10-16
- Hugging Face livestreams release of a new open-weight model — huggingface · 2026-10-16