Nathan Lambert

speaker

1,013 appearances 1 recordings 1 series first heard Nov 2024 last heard Nov 2024

Nathan Lambert’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

No recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.

newest first · ▶ plays the moment

If you collect preference data.

with different instructions, how does that change the final model?

It is a very complex attribution, but it would be nice to see.

Yeah.

I think the caveat is we don't have the human same human preference pipelines that the labs do.

This is like with whatever pipelines we have access to.

But yeah, that's the

That's

that's the way I kind of described RLH in some ways has forks

Between

um academic and industry.

Like industry cares much more about chatbot arena and user retention than academia does.

And that will probably widen and that's fine.

Uh I don't think we will ever have the ability to hill climb on Chatbot Arena 'cause we don't have a hundred million users.

I would like to know what they're doing, but it's like I don't that's the

It'll take time.

Reinforcement learning with verifiable rewards.

It might get changed in the paper, but that's the name that we're going with right now.

Yeah.

Yeah, I yeah, I agree.

Showing 801–820 of 1,013 · page 41 of 51