Similation has an even better feedback mechanism than coding agents because the world is the ground truth — every day Simile generates tens of thousands of hypotheses, watches the world, and validates which came true, enabling continuous learning.

17:50quickly know what is good and what is bad. That actually was one of the core learning mechanism for these models. And it might be easy to look at simulation as a field and say, "Well, where are you going to get the reward?" Because fundamentally, all the things you're trying to predict is it happening in the future, it's going to be hard to validate. It is true. At the same time, I actually think

18:10simulation has even better mechanism, which is the world is our ground truth. We live in the ground truth world. So, what we can do is every single day, we can be generating tens of thousands of hypotheses. Each hypothesis is mapped onto an end statement. If this happens, we know whether we can validate the simulation to be right or wrong. And we're basically watching the world every day seeing which of those

18:38hypotheses are answerable at what time. And we can basically say, a month goes by, we generated a million hypotheses, X percentage of them came true. This is a best way to learn about the world. Does it take a huge amount of compute to run these simulation environments at scale and well? Compute is an important piece of simulation. Of course, a lot of the work that we do

19:01is to make our simulation be more efficient. So, a lot of our compute initially actually goes in to create the initial breakthroughs in technology. So, it is actually exploring different ways to train, is exploring different kind of data set. Once we have a point of view, we can very quickly make it efficient. So, some of the things that I've seen, wouldn't similarly as we build this company over the year,