“If you have 10 tasks in sequence... the ER model has a certain X success rate and the VLA model has a Y success rate, now the sequencing task compounds the error”

"The Cognitive Revolution" · One Brain, Any Body: Google DeepMind's Keerthana on Gemini Robotics 2, Cross-Embodiment & Humanoids

Play from 52:05
52:05

Audio streams from the publisher’s own feed. Verbatim does not host or copy it.

What was described

describe error compounding when sequencing multiple tasks across ER and VLA models

Said nearby on the same subject

“I can have, you know, 12 tasks going now with Fable, and they're each taking multiple hours, sometimes multiple days”
JE
Jonathan Ellis
AI Engineering Podcast ·
Why it worked 12 parallel tasks; code generation 10× faster than before Share this moment
“If the tools we created could serve multiple different end users across the SOC, across the IT, across network security and have the same data… we’d be in a better place.”
PN
Palo Alto Networks Prisma AIRS platform
The Enterprise AI Show ·
Business model Share this moment
“Gemini Robotics ER 2 … is based on Gemini Flash and is available via the API, allowing developers to define the affordances available to the models as tools just like we do with digital agents.”
GD
Google DeepMind Kirthana Gopalakrishnan
"The Cognitive Revolution" ·
“When the people that are in the audience are at a dinner party, how do they describe what they do to their friends?... describe a home run in the past or a flop in the past.”
JA
Jon Acuff
The Think Media Podcast ·
How they work Share this moment

Moments like this, every Monday

The strongest new moments on your topics, in the speakers' own words. Free for three topics.

No card. No password. One-click unsubscribe.

Track a competitor?

Pro watches up to 25 names or phrases and emails you the morning after they are said.

See Pro, $29 a month

Verbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.