great research by the goat jeffrey wang. also applaud openai for the degree of transparency in this post
OpenAI shares research on chain-of-thought monitorability across model training
AIOpenAI shares new research on how chain-of-thought monitorability, covering no-CoT capability and CoT controllability, changes over the model training lifecycle. The researchers report that as models scale toward greater intelligence, they become harder to monitor through their chain of thought.
@willdepue
(1/10) Today, we’re sharing new research from @OpenAI: How does CoT monitorability (no-CoT capability and CoT controllability) evolve over the model training lifecycle? We emerged with unsurprising but sobering findings: as we scale toward more intelligent systems, models are becoming harder to monitor through their CoT. 🧵
Source details
will depue · x.comPublished · added here
Original title: great research by the goat jeffrey wang. also applaud openai for the degree of transparency in this post