Evidence receipt / evaluation
Published · transcript-backedNathan Lambert: evaluation
11 Jan 2024 Latent Space RLHF 201 - with Nathan Lambert of AI2 and Interconnects
“I think the reason this really is done on a deep level is that you're not actually trying to model any contestable preference in this.”
Source trail
Everything needed to verify it.
- Speaker
- Nathan Lambert
- Attribution
- Verified speaker
- Claim type
- evaluation
- Recorded
- 11 Jan 2024
- Publisher
- Latent Space
Transcript context
…Right. Do we just ignore it? We just, yeah, just aggregate. Yeah. I think the reason this really is done on a deep level is that you're not actually trying to model any contestable preference in this. You're not trying to go into things that are controversial or anything. It's really the notion of preference is trying to stay around correctness and style rather than any meaningful notion of preference. Because otherwise these companies, they don't want to do this at all. I think that's just how it is. And it's like, if you look at what people actually do. So I have a bunch of slides on the feedback interface. And they all publish this. It's always at the appendices of every paper.…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.