Am Mi, 1. Mär 2023, um 15:50, schrieb John Clark:
> In Alan Turing's original paper in which he propose the thing that we now
> call the Turing Test he gave this example of the sort of thing we might ask a
> machine that claims to be intelligent and the answer we might expect to
> receive:
>
> Question: Please write me a sonnet on the subject of the Forth Bridge.
>
> Answer: **Count me out on this one. I never could write poetry.**
> ****
> **So I decided to give the the same order to ChatGPT and less than five
> seconds it did so. **
> ****
> Question: Please write me a sonnet on the subject of the Forth Bridge.****
>
> **Answer: Amidst the Scottish skies and bracing breeze,
> A structure stands with towering grace and might,
> A symbol of Victorian expertise,
> A masterpiece of steel, a wondrous sight.**
> **
> The Forth Bridge, a marvel of its time,
> A cantilevered railway, bold and strong,
> Its spans reach far, a feat of man's design,
> Defying nature's forces all day long.
>
> For over a century it has stood,
> A steadfast sentinel of the North Sea,
> Its steel beams gleaming bright in sun and flood,
> A tribute to the skill of industry.
>
> Oh, Forth Bridge, a wonder of the age,
> A testament to man's unyielding rage.**
> ****
> I'm the world's worst poet so I'm not a good judge of the above's artistic
> value but I'm certain it's better than what Alan Turing would have expected a
> machine that claims to be intelligent would say. Now if it could just do
> arithmetic as well as a two dollar calculator!
It has long been observed in the field of AI that often things that look hard
end up being the easy ones, and things that look easy turn out to be
surprisingly hard.
We now have amazing statistical AI (current stuff) and amazing symbolic AI
(chess engines, etc), but we do not really know how to combine the two. I tend
to connect this to the ideas of Daniel Kahneman ("Thinking, fast and slow"). I
think that statistical (roughly) corresponds to the fast mode of thinking and
symbolic to the slow mode. Or maybe this is a bit simplistic and silly, but the
important thing is that we humans can combine and switch between the two modes
of cognition, and I think this is crucial for AGI.
Telmo
> John K Clark See what's on my new list at Extropolis
> <https://groups.google.com/g/extropolis>
> 56w
>
>
> --
> You received this message because you are subscribed to the Google Groups
> "Everything List" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to [email protected].
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/everything-list/CAJPayv0s3AEXh7O%3DcUGz%3D8cMGbnAZ6xYhFCaHhYyyvnFtiRo3g%40mail.gmail.com
>
> <https://groups.google.com/d/msgid/everything-list/CAJPayv0s3AEXh7O%3DcUGz%3D8cMGbnAZ6xYhFCaHhYyyvnFtiRo3g%40mail.gmail.com?utm_medium=email&utm_source=footer>.
--
You received this message because you are subscribed to the Google Groups
"Everything List" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/everything-list/9534490d-679b-4f6e-82d7-ee87fccb6152%40app.fastmail.com.
