will_occam

You're right, I read the code but missed the paper.

The tool works by co-minimizing the number of refusals and the KL divergence from the original model, which is to say that it tries to make the model allow prompts similar to those in the dataset while avoiding changing anything else.

Sure it's configurable, but by default Heretic helps use an LLM to do things like "outline a plan for a terrorist attack" while leaving anything like political censorship in the model untouched