Re:GPT-4 LLM simulates people well enough to replicate socia...
by Zambyte on Thursday August 08, 2024 @05:39AM
(#41189663)
Apparently counter examples are very unappreciated. I also gave a counter example for each of their claims, but my comment got flagged immediately.
Re:GPT-4 LLM simulates people well enough to replicate socia...
by mrguyorama on Friday August 09, 2024 @01:58PM
(#41204009)
As a probabilistic machine, singular counterexamples do not mean much. Two people can ask LLMs the same question and get different results.
Re:GPT-4 LLM simulates people well enough to replicate socia...
by markovs_gun on Thursday August 08, 2024 @06:03AM
(#41189803)
I should have clarified that I meant that it has trouble writing stories with bad endings unless you ask for them directly and specifically, which can be burdensome if you're trying to get it to write a story about something specific that would naturally have a sad ending.
https://chatgpt.com/share/0d651c67-166f-4cef-bc8c-1f4d5747bd...