← Back to Feed
Research Papers alignment safety model_training research

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.
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

View Original Post ↗