Modern reasoning models think in plain English. Monitoring their thoughts could be a powerful, yet fragile, tool for overseeing future AI systems. I and researchers across many organizations think we should work to evaluate, preserve, and even improve CoT monitorability. https://t.co/MZAehi2gkn
— Bowen Baker (@bobabowen) Jul 15, 2025
from Twitter https://twitter.com/bobabowen
July 15, 2025 at 04:09PM
via IFTTT
No comments:
Post a Comment