News for hackers. Stuff that matters.

A comment on UCSD: Large Language Models Pass the Turing Test.

Re:UCSD: Large Language Models Pass the Turing Test by roselan on Wednesday April 02, 2025 @11:09AM (#43557542)
I'm surprised there was no human tested for a base reference point. I'm pretty sure some of us would not pass the test held by another human.
[ Parent | on HN ]
Re:UCSD: Large Language Models Pass the Turing Test by Ukv on Wednesday April 02, 2025 @11:27AM (#43557769)
Human win rate would be 1 minus the model win rate, to my understanding. So 77% against ELIZA, 27% against GPT-4.5 with a human persona.
[ Parent | on HN ]