Grant Harvey

Yeah, the longer running the task is, I'm sure it's like the harder it is to test.

I mean, it's the same problem with medicine, right?

Where you have to do these long running human trials to figure out, you know, does this pill that or, you know,

procedure actually, you know, blast the test of time or does it kill you three years later?

simulation time compressed into a much shorter walk lock time and then try to get some of that signal okay this brings me to actually one of my biggest questions which is um which kind of came up in conversation here uh are you doing any testing with like multi-agent um swarms like i know this is kind of like the big hot topic you know open claws talking about this a lot

There's even Molt's book, which is like all of the agents talking to each other.

Like, would you ever simulate, you know, would you try to simulate, you know, a thousand people reading a textbook and, you know, how, you know, how they actually react to it?

And I have a follow up question on that, but I'll just let you react.

Related to that, do you have any sort of intuition or suspicion on whether or not the model that will be able to generalize across all of these different domains and be able to do a deep analysis and, you know, end a PowerPoint presentation?

Will that be a single model or will that be like five models that are all work together?

What's your take?

Yeah.

You're like, let's just bet on history.

Yeah.

But I will say I kind of respect that with a situation like NPM where, you know, it just got hacked with Shilud.

And I almost now I'm like, I don't want to use anything with NPM, you know, as an amateur vibe coder.

Yeah, for sure.

Yeah.

Yeah.

But it is interesting that they're like, yeah, I'm just going to do it myself instead of going for the most direct, most obvious answer.