Re:Effective GPT-4 Programming
by davrosthedalek on Wednesday November 15, 2023 @11:18AM
(#38278385)
The very start of this threat is that not expressing gratitude makes the model refuse to work.
[ Parent
| on HN ]
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.