alt Hacker NewsThis is the first time it dawned on me that mech interp is a dual-use technology which can be used to improve capabilities. Do you think overall this development will improve human understanding of AI models, or will it lead to faster capability advancement using weight-space changes that no humans read?
I think edits made directly to model weights are likely to be more interpretable and controllable than edits made by the current process of shoving a bunch of training data through gradient descent.