LLMs are not sentient, but this gimmick doesn’t prove that.
There’s nothing to indicate the human brain can’t be implemented in a Turing machine too.
There may not be proof that LLMs aren’t sentient, but there is some evidence and reason to believe that consciousness is an emergent property of quantum effects, whereas turing machines are relegated to classical mechanics. The same evidence would indicate it is unlikely that a turing machine could replicate the human brain since it uses fundamentally different layers of reality to calculate/think.
What evidence
These don’t appear to be peer-reviewed, but thanks.