Menu
Sign In Search Podcasts Libraries Charts People & Topics Add Podcast API Blog Pricing

Dwarkesh Patel

👤 Speaker
15787 total appearances
Voice ID

Voice Profile Active

This person's voice can be automatically recognized across podcast episodes using AI voice matching.

Voice samples: 4
Confidence: High

Appearances Over Time

Podcast Appearances

Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

They also added a Redis cache to simulate stale data since that's how real e-commerce sites actually work.

1356.192 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

These are the kinds of things that you might not have naively thought to do, but that Labelbox can anticipate.

1362.161 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

These details really matter.

1367.289 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

Small tweaks are often the difference between cool demos and agents that can actually operate in the real world.

1368.631 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

So whether it's correcting traces that you already produced or building an entirely new suite of environments, Labelbox can help you turn your RL projects into working systems.

1373.96 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

Reach out at labelbox.com slash dvarkash.

1383.928 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

All right, back to Richard.

1388.962 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

This alternative paradigm that you're imagining.

1390.684 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

The experiential paradigm.

1392.947 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

Yes.

1394.47 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

Yeah.

1469.749 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

I guess maybe what I meant to say is human level general continual learning agent.

1470.37 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

Yeah.

1475.315 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

What is the reward function?

1476.104 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

Is it just predicting the world?

1478.052 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

Is it then having a specific effect on it?

1479.417 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

What would the general reward function be?

1484.858 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

I see.

1527.462 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

I guess this AI would be deployed...

1527.742 View full episode →
Dwarkesh Podcast
Richard Sutton – Father of RL thinks LLMs are a dead-end

to like lots of people would want it to be doing lots of different kinds of things.

1531.437 View full episode →
← Previous Page 227 of 790 Next →
Report any issue