Jan Dubiński
@jan_dubinski_
TruthfulAI | PhD in AI | Warsaw University of Technology and NASK, working on AI safety and generative models
1.4K Following 686 Followers
"Inoculation Midtraining with Learned Neologisms". They introduce a token that tells the model where misalignment should occur. Also very cool that the authors test vulnerability to conditional misalignment (some triggers still increase misalignment a bit). A nice idea!
Authors: Kyle O'Brien, Edward Young, @RadmardPuria, @n_lie_k, @cam_tice, @tomekkorbak, @DavidDAfrica
Show more
