You know, whether that's ANSYS, Altium, Cadence, Keysight, etc., So I'm curious to hear, could you talk a little bit about how you combine these non-deterministic foundation models alongside these deterministic simulation and solver tools in order to 10x the performance of both of them?

The way we think about it is, so if you think about the sort of life cycle of engineering, right, you have, you can think about it as kind of a grid, right, where the rows are, you've got electrical, you've got mechanical, and you've got software.

And they're all interacting as you sort of co-evolve through this sort of evolution of developing a new software-defined hardware product.

So you'd start with design, right? And then you would do some degree potentially of simulation.

Oftentimes it's quick calculation, not quite simulation in the design verification, because obviously it's fastest to iterate on the design.

The minute you start making it, you start incurring this longer cycle time because you have to make the first version physically.

So you get that back and you enter, like, what people call engineering validation testing or design validation testing.

But what does that mean to build this for RF or electrical engineering? Like, what is the data that you're training this on? Are you starting from scratch? Are you building on a base model?

Mm

...

it was all possible because of scaling laws.

And, like, you know, before language models, there was a lot of machine learning where we were trying to go and solve problems at that use case level, right? We were solving, like, language translation, summarization, um, spam detection separately.

But once you, you pointed a huge model at language as the substrate and OpenAI published that seminal paper in 2020 on scaling laws, you could scale it up and it started to generalize.

Now these things can do remarkable things.

We believe we will see, and we're seeing early hints of scaling laws for electromagnetics, and this might be true for physics in general, electromagnetism being one of the four fundamental forces here, but that's sort of what we, what we think is possible.

Yeah.