via api (harder to do via chat as cleanly) you can also try showing it do a fals... | Hacker News

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

		wahnfrieden on May 16, 2024 \| parent \| context \| favorite \| on: ChatGPT-4o vs. Math via api (harder to do via chat as cleanly) you can also try showing it do a false attempt (but a short one so it's effectively part of the prompt) and then you say try again.

BOOSTERHIDROGEN on May 17, 2024 [–]

Are there any examples?

wahnfrieden on May 17, 2024 | [–]

I don’t have one but you can experiment with it

People just forget that prompting an AI can mean either a system prompt or a prompt AND a chat history, and the chat history can be inorganic

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