alt Hacker NewsDoes this actually modify the weights?
It submits prompts that get refused, then detects and modifies the weights responsible?
Like brain surgery?
Does this actually modify the weights?
It submits prompts that get refused, then detects and modifies the weights responsible?
Like brain surgery?
Yes, it submits lots of varied prompts that get refused, and then lots of varied prompts that don't get refused, then iteratively edits weights so those two groups end up in roughly the same latent space.