← Back to Feed
Joint research from MATS, Redwood, and Anthropic shows that a strategically sandbagging model can be trained to stop san
Joint research from MATS, Redwood, and Anthropic shows that a strategically sandbagging model can be trained to stop sandbagging using only weaker models as supervisors.
Original Post
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