Hi there
- š Iām currently working on formalizing theories of morality and figuring out how to get machines to recognize when they're OOD.
- š Iām interested in AI, morality, and having the future of humanity flourish
- š± Iām currently learning about interpretability techniques, transformers, and what approaches to AI Safety seem good
- šÆ Iām looking to collaborate on projects aiming to reduce risks from AI.
- š¬ Ask me about Effective Altruism, longtermism, and AI's potential for good and bad
- š« How to reach me: twitter @joemkwon
- š Pronouns: he/him/his
- ā” Fun fact: TBD