That's kinda the whole point of my comment is that things like Turing's method completely fall apart under heavy scrutiny. Further, the Turing Test specifically tells you nothing about whether or not something IS thinking, just that it MAY be. Big difference.
I see you didn't engage with the rest of my comment tho. Would you like to?
Just wanted to add this as it and stuff like it comes up pretty quickly when you research the turing test:
"On the other hand, there are several criticisms and limitations of the Turing Test as a measure of machine intelligence. Some of the main issues include:
The test focuses solely on the ability to mimic human-like behavior and communication, rather than on the underlying intelligence or consciousness of the machine.
The test is heavily dependent on the human evaluator’s subjective judgment, and may be influenced by factors such as the machine’s appearance or the human’s own biases.
The test does not take into account the possibility that a machine could be intelligent in ways that are fundamentally different from human intelligence.
The test does not consider the possibility of a machine deceiving the human evaluator, by providing pre-programmed or rehearsed responses rather than truly understanding the meaning of the questions."
LLMs would fall into the last, as they train on the "answers" so to speak and just match them to the "question".