KK Koray Kavukcuoglu Koray Kavukcuoglu SVP of Google DeepMind and Chief AI Architect at Google, running the organization day to day and overseeing Gemini model development, frontier AI research, and...

“Right now, the models are visually correct. I'd like them to be numerically correct in the engineering sense of it.”

Google DeepMind: The Podcast · AI Research & Frontier Labs · November 2026

“Right now, the models are visually correct. I'd like them to be numerically correct in the engineering sense of it.” — Koray Kavukcuoglu, Google DeepMind: The Podcast

Context

Fry asked how much the models really understand about the physical world. He says they can imagine a pink elephant but don't yet get fluids, airflow, heat transfer or collisions right, and expects that to change with the right data and environments.

Transcript

Google DeepMind: The Podcast Around 18:16 into the episode
Koray Kavukcuoglu

you a question, Mike. Like, how would you know the difference? I

Hannah Fry

don't know. You're the researcher. So

Koray Kavukcuoglu

…mean that they can actually learn the whole world and they understand? Oh, they understood a lot of things, but I don't think that we are there, that they understand the physics and the dynamics and the collisions well enough. I don't think that they understand the fluids well enough. I don't think that they understand the airflow or the heat transfer and all those kinds of things well enough. Right now, the models are visually correct. I'd like them to be numerically correct in the engineering sense of it.

Hannah Fry

Right. And correct in the sort of physics sense of it. Exactly. Okay. Do you think that's still to come? Do you think we'll get there?

Koray Kavukcuoglu

100%. Right. Yeah, we'll get there. Like, because these are computational machines that can do any kind of computation. If we actually train them in the right way with the right data in the right environment to predict the right things, they should be able to do accurate numerical computations that…

Hannah Fry

Right. Because otherwise, you don't end up with this full representation of the world that we're living in. I know one of the other things that you're working on in the early days was about the efficiency of your systems. You know more than anybody how much it takes to train a frontier model now…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

More from Google DeepMind: The Podcast