[akoboldfrying]

A one-way audio channel is indeed too weak for a person to distinguish a person from a recording, but a bidirectional audio channel is easily strong enough: the person can verbally ask the person-or-recording a question and see if it is acknowledged.

I claim that a modern frontier LLM can be given simple instructions that make it impossible for a person to reliably distinguish it from a person over a bidirectional text-only medium.

[IAmGraydon]

You’re missing my point. If you brought that voice recorder back in time a few hundred years even without the 2-way communication, people would swear there is a disembodied person in there, and you would be accused of being a witch. This is because humans always anthropomorphize things with human-like traits that they do not deeply understand. Yes, LLMs can now take human input and create human-like output. But the connection I’m trying to make is that these things are a black box to most of us, and we are yet again anthropomorphizing. We are still lacking the understanding part.

With all due respect, your claim is ridiculous. It’s incredibly easy to spot an LLM in an interactive chat. The tells are endless.

[akoboldfrying]

> With all due respect, your claim is ridiculous. It’s incredibly easy to spot an LLM in an interactive chat. The tells are endless.

https://arxiv.org/abs/2503.23674?hl=en-GB

"When prompted to adopt a humanlike persona, GPT-4.5 was judged to be the human 73% of the time: significantly more often than interrogators selected the real human participant"

My "ridiculous" claim is confirmed by science.