Speaker unverified: belief

Transcript context

…So, Jack, I mean, 1 of the the million dollar questions is, you know, like, even with a language model, it's it's stochastically sampled, know, with this temperature parameter. Same thing here. I mean, with with Genie 2, the dynamics model is using this masked git, and it was it was run iteratively. And how do you square the circle between like a stochastic neural network? And yet, it has consistency. Right? So I look over here. I look back. I look there again. The thing is back. Like, isn't it a bit weird that a sub symbolic stochastic model can give us apparently consistent, like solid maps of the world? That's a really good question. I think probably similar to language that there are some fundamental things about the world that you want to remain consistent. So with the language model, I think even though, as you said, they they can be like sarcastic models, if there are things that stated as facts in their in their context, they will still probably recall them correctly. Right? Whereas new things are where they maybe have more degrees of freedom to to change things like that. So I'd imagine in in a world like a Genie 3 generated world, if you were to move around, then maybe new things would be have some degree of of stochasticity to them. Right? But then once they've been seen once, then they should be consistent from that point forward because the model knows when to use the stochasticity. And this is kind of an emergent property from the scale that we train at. Yes. And we'll we'll save the emergent discussion. I was I was just telling the guys about my conversation with David Krakow the other day, but maybe you won't go there. But some the other really interesting thing is that so, you know, you said David Harb, you know, 2018 with Schmidt Hoover, the world models thing. And Shlomi, in the presentation, you you defined a world model as essentially being able to simulate the dynamics of something. Right? If if a world model simulates the dynamics of of a system, how could you for example, how could you measure that?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.