One thing I've been wondering, could you train a GPT-3 model to generate "better... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		InfiniteRand on Oct 27, 2020 \| parent \| context \| favorite \| on: Yann LeCun on GPT-3 One thing I've been wondering, could you train a GPT-3 model to generate "better" text prompts for another GPT-3 model By better I mean grading based on whether there is any nonsense in the output or any internal contradictions, or similar criteria

dunefox on Oct 27, 2020 | [–]

> By better I mean grading based on whether there is any nonsense in the output or any internal contradictions, or similar criteria

Sounds like you want a hard ai to determine whether a language model generates nonsense.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact