On: Learning to Reason with LLMs

[rvz]

LLMs have already beaten the Turing test. It's useless to use it when OpenAI and others are aiming for 'AGI'.

So you need a new Turing test adapted for AGI or a totally different one to test for AGI rather than the standard obsolete Turing test.

[riku_iki → rvz]

> LLMs have already beaten the Turing test.

I am wondering where this happened? In some limited scope? Because if you plug LLM into some call center role for example, it will fall apart pretty quickly.