Zuzanna Stamirowska

This is not just us, actually.

I think by now, everybody from all the labs would tell you that reasoning is this.

So we're looking at reasoning, then with reasoning capability of solving and inventing very tough problems.

So the North Star is to get to an innovator who sees what's not there, as opposed to just seeing what was there and recomposing.

Right.

So that would be the true generalization.

And then you have generalization over time.

So going towards solving problems in environments over periods of time that were not tested, that were not seen in data, etc.

In terms of safety, I think I'm not yet there to give very definite answers, but...

I'd say that part of what we're doing is actually gaining a way better scientific understanding of how the models are working and why.

For us, mapping, like very precisely mapping, understanding this passage from micro interactions and having something that we know we call the equations of reasoning, to having a scale-free structure of known laws that govern it,

This is kind of important.

It's important for safety.

Then some discussions that we have, let's say more internally, are around getting to provable risk levels of how such system will behave, you know, and if it will be kind of do what I mean machine or not.

Yeah.

Because the risks that we're looking at that are more controllable maybe for us is making sure that these models will not just by themselves won't venture into doing something just completely silly because they're hallucinating, right?

Yeah.

Something so off policy and will be just ridiculous because they would stop working like a predictable human.

Because if you think about this, if you're hiring someone, you observe them for what, a couple of hours?

Max, yeah.