Zuzanna Stamirowska

So they actually managed to produce something new that they didn't necessarily see in the training data very explicitly, right?

From having so many kind of samples of data.

Yeah, exactly.

So they've seen so much.

And these are language models, and they don't have memory.

Yes.

Correct.

So right now, when you have an LLM and you kind of start it, it's trained once.

We have these like huge models and they'll tell you how many parameters, right?

And the bigger, the better.

That would be usual, the kind of the vibe that they would be giving.

And then every time you use it, it's as if the model was waking up and always using the same brain that was set during training.

Training is very expensive because of data and compute because you need to produce a huge model.

Then it works better, of course.

You ask your question, you add some context, like a New York private document, like some whatever you're asking about, right?

Then you get your answer.

But then you relive the Groundhog Day every time.

And you have a sort of memory, Corey, exactly kind of as you said, but it's more like as if you were leaving sticky notes for yourself from the day that you know you wouldn't remember.

Yeah, I mean, exactly, exactly.

So it's like, you know, there's a big difference between having a library of knowledge versus having internalized it.