smitha milli

humans + machines = ?



Hi, I’m Smitha! I’m a 4th-year Electrical Engineering & Computer Science major at UC Berkeley. I want to make intelligent machines with a net positive impact on society.

I am a part of the Center for Human-Compatible AI and Berkeley Artificial Intelligence Research Lab. I’m lucky to have had the opportunity to work with Tom Griffiths, Anca Dragan, Stuart Russell, Marti Hearst, and David Bamman. I recently received the CRA Outstanding Undergraduate Researcher Award. This summer I will be interning at OpenAI.

I spend a lot of time thinking about meta topics and iterating on my own styles of thinking and productivity. Here is some collected research advice. Outside of research I enjoy talking to strangers and reading both nonfiction and fiction.

If you want to talk, feel free to shoot me an email at smitha dot milli at gmail dot com.

Publications

Conferences

Should Robots Be Obedient?
Smitha Milli, Dylan Hadfield-Menell, Anca Dragan, and Stuart Russell. IJCAI 2017. (upcoming)

When Does Bounded-Optimal Metareasoning Favor Few Cognitive Systems?
Smitha Milli, Falk Lieder, and Thomas L. Griffiths. AAAI 2017.
[pdf]

Beyond Canonical Texts: A Computational Analysis of Fanfiction
Smitha Milli and David Bamman. EMNLP 2016.
[pdf] [data] [press: berkeley, OTW]

Workshops

Augmenting Course Material with Open Access Textbooks
Smitha Milli and Marti A. Hearst. Building Educational Applications Workshop, NAACL 2016.
[pdf]

Teaching