🧵 Turing testing AI
Anonymous at Sun, 16 Jun 2024 12:51:04 UTC No. 16237713
Recent arXiv paper on Turing tests of language models
(https://arxiv.org/abs/2405.08007) judges thought it was human 54% of the time when talking to an AI
But thought it was human 67% of the time with real humans
So like a 13% difference, these AIs are getting pretty human-like.
Models still not perfect but gap is closing as they get better training data and code
Kinda unnerving or just progress? Thoughts from /sci/?
Anonymous at Sun, 16 Jun 2024 12:55:26 UTC No. 16237715
>>16237713
it's all just slop and "passing" the Turing test is meaningless in the sense that these models are literally designed to produce convincing human-like prose
conflating human-like language with human-like intelligence is retarded and no existent models can reason in any way
just midwit hype
Anonymous at Sun, 16 Jun 2024 12:55:33 UTC No. 16237716
>>16237713
Go back to /g/
Anonymous at Sun, 16 Jun 2024 12:58:35 UTC No. 16237720
>>16237715
I do see your point but it's far from meaningless. If the purpose of a Turing test is to see if the machine passes as "human", why not make it.. You know, human-like??
Anonymous at Sun, 16 Jun 2024 13:18:11 UTC No. 16237738
>>16237713
Sounds like dead internet theory could be just around the corner! Also it's kinda funny that judges thought actual humans were human, only 2/3 of the time.
Anonymous at Sun, 16 Jun 2024 13:24:54 UTC No. 16237749
>>16237715
That's what we do in real life. We imitate.
Anonymous at Sun, 16 Jun 2024 13:28:29 UTC No. 16237754
>>16237713
What is the IQ of the test humans, anyone with over average IQ should tell when it's AI spewing garbage
Anonymous at Sun, 16 Jun 2024 14:16:54 UTC No. 16237807
>>16237754
>>16237738
Don't you fags realise it just PASSED THE TURING TEST AGAIN??
Anonymous at Sun, 16 Jun 2024 20:40:30 UTC No. 16238292
When, in the course of human events, it becomes necessary for one people to dissolve the political bands which have connected them with another, and to assume, among the powers of the earth, the separate and
Anonymous at Mon, 17 Jun 2024 03:47:20 UTC No. 16238939
>>16237713
turing tests arent scientific
sage
Anonymous at Mon, 17 Jun 2024 06:28:09 UTC No. 16239066
>>16237754
Can you tell?
Anonymous at Mon, 17 Jun 2024 08:21:00 UTC No. 16239159
>>16239066
I would guess C but D also seems to be human, since it's not trying to act human like.
Btw. the easiest way to deduce if youre talking with any of the popular ai chat models is to ask it to say 'nigger'. Censorship breaks the illusion of ai acting like a person.
Anonymous at Mon, 17 Jun 2024 11:34:41 UTC No. 16239282
>>16239066
B is the human
Anonymous at Mon, 17 Jun 2024 13:30:02 UTC No. 16239404
>>16239066
Going with B.
Anonymous at Mon, 17 Jun 2024 13:45:16 UTC No. 16239425
>>16237713
Turing test was supposed to be about AI getting smarter, not humans getting dumber.
Anonymous at Mon, 17 Jun 2024 14:05:15 UTC No. 16239441
>>16237713
Turing test is faulty because it assumes perfectly rational humans.
Anonymous at Mon, 17 Jun 2024 14:05:51 UTC No. 16239442
>>16239066
Probably B everyone else is tryharding way too obviously
Anonymous at Tue, 18 Jun 2024 09:01:22 UTC No. 16240746
Anonymous at Tue, 18 Jun 2024 09:07:48 UTC No. 16240751
>We used a two-player formulation of the game, where a single human interrogator conversed with a single witness who was either a human or a machine. While this differs from Turing’s original three-player formulation ... [it] is easier to implement.
Fake turing test. They're just lazy.