- My undergraduate honors thesis "A Noisy Channel Model for Systematizing Unpredictable Input Variation" was presented at BUCLD 44 and will be published in the procedings.
I'm a PhD student at UT Austin who's interested in reward learning from human behavior, provable bounds on the behavior of reinforcement learning agents, and anything else required to get us from here to AI that we can trust to operate safely and with our values in the real world. I am always looking for collaborators or new projects. I answer questions about my papers to the best of my ability. If you are wondering whether or not to send me an email, please err on the side of sending it. I also accept anonymous feedback.