CMU workshop pairs philosophers and computer scientists on AI agency and interpretability

brwilder · x · 2026-09-29

A recent CMU workshop on "AI agency and interpretability" brought together philosophers and computer scientists to discuss interpreting and understanding AI, and safety questions, through the lens of rational agency. The author wrote up reflections, saying the discussions left him more excited about the area and that the two disciplines have much to offer each other. The workshop was organized by Aydin Mohseni, with links to both the writeup and the full program.

Related event: CMU Workshop Brings Philosophy and CS Together on AI Agency(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →