AI & ML interests

Safe and aligned AI research. We research situational awareness, deception, and hidden reasoning in language models.

Recent Activity

JCocola  updated a dataset 16 days ago
truthful-ai/story-imprinting
asztyber  updated a dataset about 1 month ago
truthful-ai/complex_subliminal_transfer
asztyber  published a dataset about 1 month ago
truthful-ai/complex_subliminal_transfer
View all activity