I think it's about time I had somewhere to collect my rants, ramblings and randomness, so here it is.
Caution: this blog may eventually contain such disparate topics as software, science, prediction markets, and unicycling.
Posts
Rogue Scalpel: Activation steering breaks refusal, even with benign
directions
-
*TLDR:* Activation steering can bypass refusal even when the steering
vector represents a benign concept like "brand identity" or "Portugal". It
is hard ...
3 hours ago
