undefined | Better HN

0 pointsjjani9mo ago0 comments

That's only viable if the quality of the outputs can be automatically graded, reliably. GP's case sounds like one where that's probably possible, but for lots of specific tasks that isn't feasible, including the other ones he names:

> write poetry, give me advice on cooking, or translate to German

0 comments

BenGosub9mo ago

Certainly, in those cases one needs to be clever and design an evaluation framework that will grade based on soft criteria, or maybe use user feedback. Still, over time a good train-test database should be built and leveraging dspy will do improvements even in those cases.

j / k navigate · click thread line to collapse

0 pointsjjani9mo ago0 comments

> write poetry, give me advice on cooking, or translate to German

0 comments

BenGosub9mo ago

j / k navigate · click thread line to collapse