Home

I am a research scientist on the pre-training team at Anthropic! 

I completed my PhD in Julie Shah's Interactive Robotics Group (IRG) at MIT in April 2024. In my research, I focused primarily on using cognitively-motivated principles to analyze and guide language-related neural networks. This manifested itself as (causal) probing methods to understand the linguistic properties of pre-trained LLMs and inducing more human-like emergent communication. I worked with colleagues in the EECS, BCS, and Aero/Astro departments.

Before joining IRG, I worked for two years as a software engineer on the Advanced Projects team at Amazon Robotics. Prior to that, I got my Masters in Engineering in the Robust Robotics Group at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT, concentrating in robotics. My research adviser was Professor Nicholas Roy in the Department of Aeronautics and Astronautics.

Prior to joining CSAIL as a graduate student, I earned my BS in Electrical Engineering and Computer Science and Aeronautical and Astronautical Engineering from MIT in 2015.

Recent

I defended my PhD thesis on April 25th 2024! If you'd like a recording or have questions, please reach out to me at (mycal.tucker@gmail.com)!

Info-Theory EC

Some of the my most recent work explores how trading off utility, informativeness, and complexity can be used to generate human-like emergent communication systems (example for a color domain shown on the left).