Ranking
topic on 2 shows · 3 statements across 3 episodes
3 statements about Ranking, every show
Structure Generation Reduces to a Ranking Problem When Sampling Is Scaled
“If you can sample a ton and you assume that, like, you know, if you sample enough, you're likely to have, like, you know, the good structure, then it really just becomes a ranking problem.”
Eugene Yan: LLM ranking should use pairwise comparisons for stability
“I'm actually strongly convinced that it should be pairwise and we can debate that and see how it works. And I also think that... I think it's just more reliable and stable that way.”
Marketplaces should use secondary user preferences for search ranking rather than filtering
“Work on ways to, like, make this sort of checkbox affect the ranking, but not the actual filtering is a great example of how you can listen to your users and, you know, tweak the experience, but, you know Simplify their sort of cognitive you know, load by know…”