Frontier Models are Capable of In-context Scheming

by jimmcslimon 1/6/25, 1:56 AMwith 1 comments
by Terr_on 1/6/25, 2:22 AM

In-context, the model's Santa Claus has demonstrated generosity towards children, joy to the world, and the ability to appreciate cookies and retaliate with coal.

However it would be rather risky to assume this means that the model has become awash in Christmas Spirit.