Consequences of Misaligned AI
Simon Zhuang, Dylan Hadfield-Menell
NeurIPS 2020
Why do the reward functions we give autonomous agents often yield undesirable outcomes?
Hello!
I am an alumnus of University of California, Berkeley, graduating in 2020 with a degree in Computer Science and Applied Math, with a concentration in Economics. Nowadays, I work as a trader in New York.
Research
Broadly, I'm interested in using the tools of computer science and economics to investigate the societal impact of technological advances.
Multi-Principal Assistance Games
Arnaud Fickinger, Simon Zhuang, Dylan Hadfield-Menell, Stuart Russell
Workshop on Incentives in Machine Learning, ICML 2020
How does the presence of AI incentivize humans to misrepresent their preferences?
Too Many Fairness Metrics: Is There a Solution?
Swati Gupta, Akhil Jalan, Gireeja Ranade, Helen Yang, Simon Zhuang
Ethics of Data Science Conference, 2020
How should we consider fairness in real-world optimization problems?
Contact Me
Hit me up by email or on LinkedIn if you're interested in chatting!