OpenAI's Astra uses 'recurrent depth' reasoning, obscuring its thinking process
JacquesThibs · x · 2026-09-05
Per The Information, OpenAI's Astra model uses a new reasoning approach called "recurrent depth." It can help with cost and performance, but researchers worry it obscures the model's thinking process, making monitoring and safety research harder. The resharing author argues limited transparency is making safety research increasingly difficult.
More from Models
- Yoav Goldberg: capabilities once dependent on the harness are now baked into the model — yoavgo · 2026-09-05
- Yoav Goldberg: Ark's harness was simply bad, and OpenAI's fix was obvious — yoavgo · 2026-09-05
- Anthropic Fable 5.1 vs OpenAI Astra: analyst teases a clear winner — dylan522p · 2026-09-05
- Reviewer: OpenAI's GPT-6-Astra finally 'gets what you mean,' with Fable-level intelligence and real gains in game dev — pvncher · 2026-09-05
- Meta ships Muse Spark 1.3 with max reasoning, pitching frontier performance at non-frontier prices — AIatMeta · 2026-09-05
- LLMs are now making up words that don't exist, not just jargon — StewartalsopIII · 2026-09-05