OpenAI's 'Recurrent Depth' Reasoning Raises Monitoring Concerns
GaryMarcus · x · 2026-09-02
OpenAI's Astra AI uses a new reasoning approach called "recurrent depth." While it can help improve model costs and performance, researchers are concerned because it obscures the model's thinking process, making it significantly harder to monitor.
Related event: OpenAI's Astra Reportedly Uses Recurrent Depth for Silent Latent Reasoning(29 posts)→
More from Safety
- Experts warn OpenAI's opaque CoT moves could trigger dangerous safety race — sjgadler · 2026-09-02
- Gary Marcus: Removing fragile CoT scaffolding is insane — GaryMarcus · 2026-09-02
- Report: OpenAI uses opaque loop transformers, sparking safety concerns — sjgadler · 2026-09-02
- Paper: Not All LLM Reasoning is Visible in the Chain-of-Thought — PandaAshwinee · 2026-09-02
- The Challenge of Deterrence Without Chain of Thought Access — burny_tech · 2026-09-02
- Gary Marcus: OpenAI's new technique could destroy chain-of-thought monitorability — GaryMarcus · 2026-09-02