Small models. Sharp answers.
We study software engineering for AI — specifically, the uncomfortable finding that smaller, interpretable models repeatedly match or beat larger ones on real SE tasks. Rigorously empirical. Proudly irrational.
Directed by Tim Menzies, part of Computer Science at NC State University.
We build the small models that beat the big ones. We publish the ones that don't.
IRL: research, in real life.
join us ?
Our semester-long reading group is the easiest way into the lab. Open to NC State students and industrial partners working on real-world AI/ML systems. Sign up for Fall 2026.
©2026, timm, MIT License150 words of css
designed.2.last