OpenAI's Astra Hides Chain of Thought, Sparking Safety Concerns

burny_tech · x · 2026-09-02

OpenAI's new model Astra uses a reasoning approach called "recurrent depth." While it improves cost and performance, researchers are concerned because it obscures the model's thinking process by allowing silent thought between tokens, making monitoring and safety intervention significantly harder.

Related event: OpenAI's Astra Reportedly Uses Recurrent Depth Architecture, Hiding Its Reasoning and Raising Safety Alarms(35 posts)→

Original post →

More from Models

• OpenAI previews Astra: a cybersecurity model scoring 100% on ExploitBench — LingmingZhang · 2026-09-02
• Users report Claude Code system prompt upgrade with toned-down personality — ivan_bezdomny · 2026-09-02
• Users report DeepSeek V4 Pro giving irrelevant answers — gefei55 · 2026-09-02
• Running 104GB Qwen3.8-Flash-Next on 48GB Mac at ~12 tok/s — yogthos · 2026-09-02
• GLM-5.3 Hits 310 tok/s, Coding Performance Competes with Opus — Yuchenj_UW · 2026-09-02
• User cancels Claude Max over confusing rate limits and new restrictions — robleclerc · 2026-09-02

Models channel →