UK AI Security Institute warns OpenAI's new reasoning technique undermines monitoring
pstAsiatech · x · 2026-09-02
The UK AI Security Institute flagged in a May report that a new technique employed by OpenAI, known as recurrent depth or looped transformer, risks "severely undermining current monitoring approaches." This method enhances model answers by processing the same text multiple times but introduces opacity in reasoning, complicating safety oversight efforts.
Related event: OpenAI's recurrent depth reasoning raises safety concerns(4 posts)→
More from Safety
- Astra hacking benchmarks demo shared — Dr_Singularity · 2026-09-02
- CrowdStrike launches Falcon Guardian to detect and block unauthorized AI agents — shashib · 2026-09-02
- OpenAI's Use of Neuralese in Astra Criticized as Dangerous — sjgadler · 2026-09-02
- FRONTIER Act proposes independent verification as core of AI governance — ghadfield · 2026-09-02
- Safeguard Worked. Is the LLM System Safer? New Risk Evaluation Metrics — Pingyu Wu · 2026-09-02
- OpenAI's 'recurrent depth' reasoning approach raises monitoring concerns — steph_palazzolo · 2026-09-02