News for hackers. Stuff that matters.

A comment on GPT-4 LLM simulates people well enough to replicate social science experiments. Parent comment

Re:GPT-4 LLM simulates people well enough to replicate socia... by IIAOPSW on Wednesday August 07, 2024 @10:37PM (#41187598)
Yes, but with the caveat of in some very specific cases no.

I spent a good deal of time trying to get it to believe there was a concept in the law of "praiseworthy homicide". I even had (real) citations to a law textbook. It refused to believe me.

Given the massive selling point of ChatGPT to the legal profession, and the importance of actually being right, OpenAI certainly reduces the "high trait agree-ability" in favor of accuracy in this particular area.

[ Parent | on HN ]
Re:GPT-4 LLM simulates people well enough to replicate socia... by AnthonBerg on Thursday August 08, 2024 @02:19AM (#41188633)
There’s a way to apply the concept of praiseworthy homicide – metaphorically – to your battle with it.
[ Parent | on HN ]