I am an undergrad at MIT studying Computer Science. I’m passionate about making AI and computing systems safe and efficient so they can benefit humanity at large; specifically, I am interested in interpretability and performance engineering.

Experiences

I currently work on understanding LM’s internal world models in Prof. Jacob Andreas’s group, and have previously worked on training dynamics with Prof. Max Tegmark.

I’ve also thought a lot about performance engineering as a TA for 6.106 (6.172) Software Performance Engineering and as an intern at Together AI and WeRide.ai. See a list of my publications here.

News

• September 25, 2024: Paper “Algorithmic Progress in Language Models” is accepted as a poster at NeurIPS 2024!
• June 24, 2024: My paper “Survival of the Fittest Representation” is accepted to the “Mechanistic Interpretability Workshop at ICML”!

Contact

You can email me at carlguo[at]mit[dot]edu. You can also find me on GitHub, Google Scholar, LinkedIn, or Twitter. Submit anonynous feedback to me here.

My pronouns are he/him/his. I can speak English and Chinese Mandarin.

Misc

I went to St. Mark’s School in Southborough, MA. Before coming to the US for high school, I spent most of my life in Jinan, China, where I’m happy to call home.

In Winter 2023, I competed in MIT Battlecode and won 2nd place (read more here). I used to compete in college-level Mock Trial, for which I coded a website for automatic tournament tabulation.

In my free time, I do stand-up comedy, cook, and make coffee.

Live the questions now. Perhaps you will then gradually, without noticing it, live along some distant day into the answer. —Rainer Maria Rilke