The very start of this threat is that not expressing gratitude makes the model r... | Hacker News

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

		davrosthedalek on Nov 15, 2023 \| parent \| context \| favorite \| on: Writing a GPT-4 script to check Wikipedia for the ... The very start of this threat is that not expressing gratitude makes the model refuse to work.

meiraleal on Nov 15, 2023 [–]

It doesn't refuse to work. It behaves differently and yields better results with politeness. Coming from a large language model, the occurence of this phenomena is intriguing for some of us.

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