Corey Knowles

I'm like, that's totally not, you made that up, man.

It made up.

It's ridiculous.

Yeah, I think a large part of it is how you apply or use the LLM.

And this is, I think, why LLM is so effective at coding, is that there is a right answer.

There's a right or wrong answer.

You can say, hey, does the button do the thing?

And you can write a test for it.

And then you keep on doing it, and the LLM keeps entering until the test turns green.

And I think in a lot of real-world cases, there is not that.

You cannot verify the veracity of a statement as easily as code.

Or like the IOI, for example.

In a math competition,

you can sort of go through it line by line and be like, does it work?

Is the proof correct or not?

Largely speaking, you can test it, right?

Whereas in a lot of other types of work, you cannot.

And I think over the next year or two, a lot is going to come to this verification, if you will.

Yeah.

To be honest, the space of UIs is actually not very large, especially for internal applications.