For the entire span of my life, people have tried to develop AI systems and anticipated a day when those systems can pass the Turing Test.
Now that day has arrived, and no one seems to care about Turing Tests anymore. Why not?
Is it that
1) We're not actually there? It would take more than a few simple patches (google the answer to arithmetic questions!) on top of ChatGPT to pass a turing test?
2) Arriving there makes it clear that the Turing Test never was the right metric?
3) We're way to busy trying to figure out how LLMs are going to upend out lives to be worrying about something so academic?
4) The entire misinformation age has soured us on the idea of something like a Turing Test for ascertaining anything?
Something else?
@ct_bergstrom I'm not convinced current-generation LLMs are that close to fooling a well-structured Turing test with trained observers. The tendency for the LLMs to make stuff up will hold them back. Inventing and maintaining a detailed biography and persona will be a problem. The test design should encourage probing that.
Another reason the Turing test remains interesting, also tragic given his life's arc, is that he draws a parallel to avoiding discrimination against people when designing it.
Carl T. Bergstrom
Dan Fain, Ph.D.