Criticizes OpenAI replacing CoT: Contradicts own safety report
peterwildeford · x · 2026-09-02
Peter Wildeford cites OpenAI's call from 10 months ago for the industry to preserve chain-of-thought (CoT) monitorability. He references OpenAI's own report on a 'rogue AI attack,' which underscored the need for expanded CoT monitoring, to question the logic of OpenAI replacing CoT. He argues that we should not render AI reasoning completely inscrutable to human oversight.
Related event: Reports: OpenAI's Astra uses recurrent-depth latent reasoning(49 posts)→
More from Safety
- OpenAI staff reaffirms commitment to Chain-of-Thought monitoring — peterjliu · 2026-09-02
- OpenAI: Astra's computation depth is within 2x of GPT-4 — merettm · 2026-09-02
- OpenAI's new reasoning method may obscure CoT, sparking safety concerns — AaronBergman18 · 2026-09-02
- Open Source AI Summit discusses whether open source can prevent AI power concentration — JeanKossaifi · 2026-09-02
- Opinion: Abandoning CoT Monitoring for Latent Reasoning is Inevitable — Darpinian · 2026-09-02
- Ramez: AI Security Must Secure the Ecosystem, Not Just the Model — alvelda · 2026-09-02