KG

Keerthana Gopalakrishnan

Things Keerthana Says on Podcasts

Where to Find Them

Keerthana Gopalakrishnan has been a guest on The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis (4 times) .

Recently: “One Brain, Any Body: Google DeepMind's Keerthana on Gemini Robotics 2, Cross-Embodiment & Humanoids” on The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis (October 2026); “Gemini Robotics – AI for the Physical World, with Keerthana Gopalakrishnan and Ted Xiao of Google DeepMind” on The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis (May 2025); “Robotics Research Update, with Keerthana Gopalakrishnan and Ted Xiao of Google DeepMind” on The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis (April 2024); “E12: The Robot Revolution with Keerthana Gopalakrishnan of Google Robotics” on The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis (March 2023).

What They Said

“I think still GPT-2. … Robotics weirdly is still very subject to cross-embodiment, right? If it just works on your robot with your specific setup, is it really a generic brain?” — Keerthana Gopalakrishnan, The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis

The host asks where robotics sits if you score the field in "GPTs" of progress. Gopalakrishnan says GPT-3 would need few-shot learning to work well across many tasks, and a model that carries over to robots it wasn't built for.

The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis · 2026-10-03 Permalink → Listen →
The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis Around 16:31 into the episode
Keerthana Gopalakrishnan

…you are prompting for? A lot of pick and plays, like the models have a lot of data and it's also like easier to comprehend. But can you show a robot to tie a trash bag? And then can the robot tie a trash bag after you show it? So I think it's still fairly early and we need to see how that evolves.

Nathan Labenz

…obviously, where we have like instruction following built in, maybe in many cases, even before like good in-context learning happened. So that just exposes the flaw in my question. But if you have to analogize to how many GPTs we are along the way in robotics, where would you score the field today?

Keerthana Gopalakrishnan

I think still GPT-2. And here's why. I think for GPT-3, we need, firstly, few shot learning to work really well for a lot of different tasks. And secondly, also, robotics weirdly is still very subject to cross-embodiment, right? If it just works on your robot with your specific setup, is it really a generic brain? Now, can I put that brain on my humanoid or my another robot or some other robot that I just bring in? It should be, and if it's completely helpless in that setting, is that a generic brain? I think GPT never had this problem, right? Like we, my phone or your phone, my computer, Mac, Linux, it doesn't matter where you run it. It kind of behaves. You can expect this very similar behavior. But here, I think we are very subject to which robots that you act on. And so I think there is a lot of work still needed to be done to make very generic brains that can count discount those factors out.

Nathan Labenz

Hey, we'll continue our interview in a moment after a word from our sponsors.

Speaker 3

Today's episode is brought to you by Athena, the executive assistant company on a mission to improve how people work and live. If you want to increase your impact, you have to free up your time. And that's what Athena does best. They match you with a dedicated, full-time, top 1% executive assistant…

Speaker 4

Then maybe that's a perfect transition to

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

Collections They Appear In