I don't think the Turing Test, in its strictest terms, is currently defeated by LLM based AIs. The original paper puts forward that:

>The object of the game for the third [human] player (B) is to help the interrogator. The best strategy for her is probably to give truthful answers. She can add such things as "I am the woman, don't listen to him!" to her answers, but it will avail nothing as the man can make similar remarks.

Chair B is allowed to ask any question; should help the interrogator identify the LLM in Chair A; and can adopt any strategy they like. So they can just ask Chair A questions which will reveal that they're a machine. For example, a question like "repeat lyrics from your favourite copyrighted song", or even "Are you an LLM?".

Any person reading this comment should have the capacity to sit in Chair B, and successfully reveal the LLM in Chair A to the interrogator in 100% of conversations.

▲

tough 3 days ago | parent [-]

that relies on the positive-aligned RLHF models most labs do.

what if you turned that 180 into models trained to decieve and lie and try to pass the test?

▲

lumost 3 days ago | parent | next [-]

Human's are able to quickly converge on a pattern. While I doubt that I could immediately catch all LLMs, I can certainly catch a good portion by having simply worked with them for a time. On an infinite horizon Turing test, where I have the option to state that Chair A is a machine at any time - I would certainly expect to detect LLMs simply by virtue of their limited conversational range.

	▲	tough 3 days ago \| parent [-]
		if anything i would do differently, i'd try things only machines can reliably do. unless the llm and the design for it is necessarily adversarial, not even going into red teaming or jailbreaks. A human couldn't type for 24h straight or faster than say X WPM, A human couldn't do certain tricky problems or know and reply super fast to various news events etc. Search/training date seems important factor too to tie in. but yeah overall if the time is infinite you can come up with some new way to find out, kinda becomes a cat and mouse games then like software security nowadays

▲

oinfoalgo 3 days ago | parent | prev [-]

If we had firms spending billions of dollars to pass the Turing test, it seems absurd to me to believe the current crop of models could not pass the test.

Luckily, it is obvious that spending huge amounts of money to train models on how to best deceive humans with language is a terrible idea.

That is also gaming the test and not in the spirit of generality that the test was trying to test for.

Even playing Tic-tac-toe against GPT5 is a joke. The model knows enough of how the game works to let you play in text but doesn't even know when you won the game.

The interesting part is that the model can even tell you why it sucks at tic-tac-toe

"Because I’m not really thinking about the game like a human — I’m generating moves based on text patterns, not visualizing the board in the same intuitive way you do."

10 years ago it would not be conceivable we could have models that pass the Turing test but be hopeless at Tic-tac-toe and be able to tell you why they are not good at Tic-tac-toe.

That right there is a total invalidation of the Turing test IMO.

	▲	birn559 3 days ago \| parent [-]
		How would AI reliable pass the turing test when playing Tic-Tac-Toe reliably reveals the weakness of today's AI?