A korrentour readingWhat is a korrent?
Weaker AI models match stronger ones on simple prompts, but strong models are increasingly preferred as prompts get more challenging.
Drawn from what Chip Huyen said
What Chip Huyen actually said
Word for word, with the source under each one. They did not write this page.
Engineer and writer on machine-learning systems
One pattern is that for simple prompts, weak models can do (nearly) as well as strong models. For more challenging prompts, however, users are much more likely to prefer stronger models.
Where this was said
↗Predictive Human Preference: From Model Ranking to Model Routinghuyenchip.com
All 3 korrents from this piecethis one is 2nd
Added to korrents 28 Feb 2024 · How quotes work · Something wrong? Tell us
Do you hold this korrent?Do you also believe this?
Related korrents
Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.