Grant Harvey

But this part here doesn't.

How how is the iteration process with the agent?

Like, can you go in, check its work and then see where it went off and give it notes?

Or how does the actual feedback mechanism work there?

Yeah, that's really smart to do that.

You know, right at the end, make sure like, okay, the ultimate conclusion, sure, it might be sound logic in the context of what you're doing.

But when you look at it back in the context of the law, is there actually legal precedent for this?

Exactly.

Yeah, yeah.

We've all heard the horror stories of lawyers citing fake cases generated by AI.

I think they get headlines.

I haven't seen headlines of them lately.

I think lawyers are kind of buttoning themselves up, but we've definitely seen that.

Lesson learned.

Yeah.

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?