Heretic removes restrictions from language models

I have a chinese IP camera. From superficial research I know it has some CVEs to take control of it. Unfortunately, I don't have the technical knowledge to perform an attack and run some software to extend the camera's functionalities. No model from a provider accepts my RE and hacking requests, so these abliterated ones have been vital to reclaim possession over my stuff

Keep a close eye on abliterated and "heretic" open weight models. They will be outlawed first.

Looks like a well engineered, automated abliteration pipeline. The claims seem a bit overstated though, since the metrics mentioned are cherrypicking refusal count and KL divergence, both of which make the outcome seem the most dramatic.

Can the load-bearing gaps that are worth being flagged for pinning down be abliterated out of a model?