Chain-of-Thought Controllability in Reasoning Models
Press Space for next Tweet
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…
Topics
Topics
We doomscroll, you upskill.Get the stories and ideas that matter
slop ⇢ substance ⇢ signal5 minutes a week, zero spam.