alignment research

1 free resource on this topic. Everything here is free and hand-picked. You can also search within this topic.

FreeWebsite

Technology & Ethics

Truthful AI

A Berkeley-based nonprofit led by Owain Evans that researches situational awareness, deception and hidden reasoning in language models. The site lists its papers, including work on emergent misalignment and subliminal learning.

#AI safety#alignment research#Owain Evans

truthful.aiAdded Oct 20, 20260 opens