There is a stark difference between the behavior you can get out of a Chat inter... | Hacker News

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

		swordsith 12 days ago \| parent \| context \| favorite \| on: An AI agent published a hit piece on me – more thi... There is a stark difference between the behavior you can get out of a Chat interface LLM, and its API counterpart, and then there is another layer of prompt engineering to get around obvious censors. To think someone who plays with AI to mess with people wouldn't be capable of doing this manually seems invalid to me.

		help

zahlman 12 days ago [–]

There is also a stark difference between being capable of making those tweaks, and noticing and caring about the deficiencies.

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