Emil Ryd
@emilaryd
ai safety research and physics olympiads
294 Following 566 Followers
New paper from MATS, Redwood, and Anthropic!
If a capable model is strategically sandbagging, can we train it to stop when the only supervision we have comes from weaker models?
We find that we can!
Work done as part of the Anthropic-Redwood MATS stream. https://t.co/6Md3XMD6A6
Show more
