News for hackers. Stuff that matters.

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

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 ]

There are no comments on this comment yet.