
Mav Levin
@mavlevin
Hacked my high school's grading system. Then found 0days for national security. Now @Stanford student | 🏳️🌈
ID: 980127659895205889
https://mavlevin.com/ 31-03-2018 17:00:18
883 Tweet
2,2K Followers
908 Following









Human behaviors often don't correspond to maximizing a scalar reward. How can we create aligned AI agents without inferring and maximizing a reward? I'll have a poster at MHFAIA@ICML2024 at 11:30 on a scalable contrastive objective for empowering humans to achieve different goals










