It would be interesting to see how reliability changes based on the exact respon... | Hacker News

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

skybrian on July 29, 2020 | parent | context | favorite | on: Teaching GPT-3 to Identify Nonsense

It would be interesting to see how reliability changes based on the exact response you asked for.

arram on July 29, 2020 [–]

My next experiment.

lt on July 29, 2020 | [–]

I'd try with a few different responses according to the type of nonsense question: "That doesn't make any sense", "How could I know that?"/"No one knows that", "That's a matter of opinion", etc.

Consider applying for YC's Winter 2027 batch! Applications are open till November 2.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact