Press Space to continue
Chain-of-Thought Controllability in Reasoning Models
Press Space to continue
We're publishing a new evaluation suite and research paper on Chain-of-Thought (CoT) Controllability. We find that GPT-5.4 Thinking shows low ability to obscure its reasoning—suggesting CoT monitoring remains a useful safety tool. https://openai.com/index/reasoning-model…
open on x · 4 viewsViews and clicks count once per visitor per day. Clicks are opens of this post on X.