🛡️ Safety
AI Alignment Forum
1 min read
Prompted CoT Early Exit Undermines the Monitoring Benefits of CoT Uncontrollability
Code: github.com/ElleNajt/controllability tldr: Yueh-Han et al. (2026) showed that models have a harder time making their chain of thought follow user instruction compared to controlling their response (the non-thinking, user-facing output). Their CoT controllability conditions require the models’ thinking to follow various style constraints (e.g. write in lowercase, avoid a word), and they measure how well models can comply with…
