applied physics

And so I was pretty frustrated with that.

And then I had a chance to actually, after last year's class, started spending some time at the Applied Physics group on campus, working on evaluating frontier models on their ability to reason about condensed matter physics data.

And thank you, ZX, for the opportunity for that.

And we came up with a draft paper for submission to NeurIPS that benchmarked a bunch of last year's Generation Frontier models, and they were just terrible.