Grant Harvey

They'll cite a fake case.

And I think there was like one a week for a little while when we were covering this.

So, yeah, I mean, the hallucination factor, right, is really huge here.

I guess just like in the legal realm in general and specifically what you did with deep research.

How are you thinking about hallucination problem solving when the stakes are as high as, you know, legal legal ramifications for for failure?

Yeah.

There's a debate between open source and closed source.

How do you think about that in your benchmarks personally for you and also for the work that you do?

Are you worried about open source models and using them in production or how do you feel about it?

Yeah.

That's awesome.

Changing gears slightly, because we just mentioned agents again.

So Deep Research was definitely, I would say, the first killer app for agents.

Someone asked me, what is the best killer app for agents?

I'm still not figuring out what they're good for.

And I was like, well, do you use Deep Research?

He was like, yeah, I use it every day.

I was like, well, then it's Deep Research.

Deep Research is the killer app.

But what do you think, just from your own personal opinion, what the next breakthrough agent use case will be?