- ๐ Hello universe! Iโm @phiriv
- ๐ Interested in evolutionary computing, reinforcement learning, interpretability, and AI alignment
- ๐ฑ Currently learning about ways to combine evo methods & RL
- ๐๏ธ Looking to collaborate on machine learning projects related to reward hacking + explainability
- ๐ซ [email protected]
- ๐ philipperivet.ca
phiriv / intro-to-ml-safety Goto Github PK
View Code? Open in Web Editor NEWNotes & exercises for Dan Hendryck's course
License: MIT License