
"(My understanding of) What Everyone in Technical Alignment is Doing and Why" by Thomas Larsen & Eli Lifland
LessWrong (Curated & Popular)
00:00
Evaluating L M Power
e l k seems like one of the most promising angles of attack on the problem. Beth barns, beth is working on generating a data set that we can use to evaluate how close models are to being able to successfully seek power. The overall goal of the project is to assess how close a model is to being dangerous,. for example, so we can know if it's safe for laps to scale it up.
Play episode from 16:59
Transcript


