Preaching to the choir, Greg. See Hutter Prize. I brought up the Turing
Test as a way of asking my question about GPT-3's "statefulness". I took
this approach because, as you obviously are painfully aware, lots and lots
of people get excited about Turing Test style demos of GPT-3 -- so someone
m
Actually it seems like it is part of the OpenAI sales pitch. They are
saying they are in the "AGI space" and banking on people applying the
Turing test. If it seems like it is AGI it's AGI. That's the
cold-blooded marketing plan. And they have a lot of money and a lot of
computing power to sell it.
I think the public will be satisfied with AI and think it is AGI if it
passes the Turing test for them.
Developers will never be satisfied with just that, since we'll
naturally suspect it's a trick. The developers are a micro-minority.
On 6/10/22, Greg Staskowski wrote:
> The Turing Test i
The Turing Test is useless.
Period. Full stop. #NotEVenWrong.
GJS
On Wed, Jun 8, 2022 at 3:55 PM James Bowery wrote:
> Correct me if I'm wrong, but all of the attempts to use GPT-3 to pass the
> Turing Test are "stateless" in the following sense:
>
> All prior inputs to GPT-3 are appended to t
Correct me if I'm wrong, but all of the attempts to use GPT-3 to pass the
Turing Test are "stateless" in the following sense:
All prior inputs to GPT-3 are appended to the current input, and the whole
mess is sent as a single input to GPT-3 always in the same state.
GPT-3, itself, doesn't keep tr
