Dang Nguyen

I’m a Computer Science PhD student in the Chicago Human+AI Lab at the University of Chicago advised by Chenhao Tan. I also work with Ari Holtzman as part of a wider Communication & Intelligence initiative.

I’m interested in AI evaluation, including evaluation of the evaluators. What biases and tendencies do models have, and how might their widespread adoption change the way we do things, such as in communication and science? When unintended biases become values that models stand by, how do we ensure that their values are compatible with ours? As such, I’m also broadly interested in AI safety and alignment.

A related question I find fascinating is how do we get AI to write better. This has eluded progress despite impressive strides made in more verifiable domains. The next step change in AI will happen when they can write a paper scientists find “insightful”.

Outside of research, you can find me training Brazilian Jiu Jitsu or lifting weights. If you’d like to chat, feel free to reach out!