Evidence receipt / evaluation
Published · transcript-backedJeffrey Wang: evaluation
8 Jun 2023 Latent Space From RLHF to RLHB: The Case for Learning from Human Behavior - with Jeffrey Wang and Joe Reeve of Amplitude
“Now, when we talk about large behavioral models or like actually embedding events, there are many, many trillions of those. And yeah, Postgres probably doesn't work there.”
Source trail
Everything needed to verify it.
- Speaker
- Jeffrey Wang
- Attribution
- Verified speaker
- Claim type
- evaluation
- Recorded
- 8 Jun 2023
- Publisher
- Latent Space
Transcript context
…Yeah, yeah, yeah. Just to clarify that a little bit more, we're not putting individual end user vectors or end event vectors. We're putting in taxonomies. So if I'm DoorDash, my taxonomy is add to cart, checkout, purchase, browse. That's the cardinality. And so that's actually small. It's on the order of tens of millions. And so yeah, you use stuff that in Postgres, no problem. Now, when we talk about large behavioral models or like actually embedding events, there are many, many trillions of those. And yeah, Postgres probably doesn't work there. Yeah, actually I wanted to comment on this slightly before, which is separating taxonomies from the actual data is one way you protect your customers against prompt injection. It's something that Simon Willison has been talking about where you want to have like query for one thing, but essentially no knowledge of the actual underlying data, just the taxonomy. So it's good practice.…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.