neural networks

“Frankly, almost everything that is, that matters, Ah, was basically in the past four years. Like, there were a lot of things that fit in academics that were before that, and you know, and they were mostly dealing with models that were under a billion parameter…”

“Outside of this, like, where we don't have good symbolic models, like, synthetic data obviously, like, doesn't make any sense. So synthetic data is not a magic wand where it'll work in all cases, in every case, you know, whatever. It's just where we as humans …”

“If you've got really good interp, you can start to reframe neural networks, not as just a tool for automating things that we already know how to do, but as a tool for discovery, as like a lens through which you can see patterns in data that would otherwise Be …”

“There's like actually so many of these kind of more scientific questions that I would like love to explore sometime, but then it really kind of conflicts with like empirical stuff, you know, like unfortunately at any given moment in time, it doesn't seem like …”

“Where if you build equivariance in, basically, once you've trained it in one orientation, it will understand it in any other orientation. So that means you need a lot less data to train these models.”

“And like, for example, we now know the neural network is the correct architecture.”

“Neural operators enable because they model inputs and outputs as continuous functions that can be infinitely resolved, that can have infinite discretization. And now we can have You know, at inference time, you can give it now inputs and ask for outputs at any…”