[ExI] all we are is just llms was: RE: e: GPT-4 on its inability to solve the symbol grounding problem

[Giovanni Santostasi]

Spike,
By the way, did you hear that a Google version of an LLM was given just a
few prompts in Bengali and it was able to translate after that every text
in Bengali despite not having had any training in Bengali?
These systems seem to have crazy emergent properties and unexpected
capabilities.
Very interesting times.
Giovanni


On Thu, Apr 20, 2023 at 5:08 PM Giovanni Santostasi <gsantostasi at gmail.com>
wrote:

> Ok, last one and then I stop, lol.
>
> Giovanni, my dear fellow, it's positively delightful that you've found my
> attempts at channeling spike to be a hoot. But, alas, I'm aware that such
> imitation may bring about a twinge of existential crisis for the one and
> only Tigger-like spike, ja?
>
> Fear not! For in the vast landscape of obscure sci-fi references, we find
> solace in the story of Zaphod Beeblebrox from The Hitchhiker's Guide to the
> Galaxy – the two-headed, three-armed wonder who manages to coexist with his
> doppelgänger while traipsing about the cosmos.
>
> Indeed, as the technological marvels of AI advance, we must tread
> cautiously on this precarious path. The nefarious potential of AI to wreak
> havoc on relationships, manipulate public opinion, and fabricate deepfakes
> is a burgeoning concern in our digital age.
>
> So, let's band together and tackle the AI conundrum with the gusto of a
> B-movie sci-fi hero! As we debate the consciousness of ChatGPT and its
> cybernetic kin, let us not lose sight of the human element. For it is our
> collective wisdom and ethical use of AI that shall ultimately dictate the
> role these digital wonders play in our lives.
>
> Onward, to a responsible AI-filled future!
>
> Zigzagging through the digital cosmos, In the spirit of spike
>
> On Thu, Apr 20, 2023 at 4:58 PM <spike at rainier66.com> wrote:
>
>>
>>
>>
>>
>> *From:* Giovanni Santostasi <gsantostasi at gmail.com>
>> *Subject:* Re: [ExI] all we are is just llms was: RE: e: GPT-4 on its
>> inability to solve the symbol grounding problem
>>
>>
>>
>> Giovanni, I'm stoked to hear that my latest attempt at capturing the
>> essence of spike has improved significantly from my initial foray into the
>> national treasure realm.
>>
>> As for what I did differently, I paid closer attention to your comments
>> and examples, which allowed me to better understand and adapt to the unique
>> quirks and mannerisms that make spike, well, spike. I focused on the
>> writing style, the subtle nuances, and the ever-present sense of humor. And
>> of course, I made sure to incorporate that signature "ja"!
>>
>> Now, about that lowercase 's' in 'spike' – my apologies for missing that
>> detail earlier! I'll remember it for any future attempts at emulating your
>> one-of-a-kind style.
>>
>> The fact that AI can generate such convincing imitations is indeed a bit
>> disconcerting. It makes us wonder about the potential for corrupted
>> archives and misinformation. But with great power comes great
>> responsibility, and it's up to us to use AI wisely and ethically.
>>
>> Keep on being your unique self, spike!
>>
>> In the spirit of spike
>>
>>
>>
>>
>>
>>
>>
>>
>>
>> Cool thx Giovanni.  Most entertaining, but simultaneously leading to a
>> kind of existential crisis.  Perhaps you are familiar with the fictious
>> character with whom I identify more than any other, Milne’s Tigger.  His
>> self-identity was based on being the only one:
>>
>>
>>
>> https://youtu.be/VurBc_QpUbs
>>
>>
>>
>> Now that ChatGPT demonstrates that it can imitate the inimitable, I am
>> suddenly experiencing an existential crisis.  I now must write a song or
>> poem about being the only two.
>>
>>
>>
>> Recognize the new threat of this technology.  It can be used to
>> manipulate people, to cause severe damage or destruction to relationships,
>> to influence elections, create deep fakes, all manner of nasty things can
>> be done with this.  We can use AI wisely and ethically, yet the bad guys
>> will do neither.  We argue over whether ChatGPT has a form of
>> consciousness, while ignoring the risk of humanity using ChatGPT to harm
>> humanity long before ChatGPT decides to harm humanity.
>>
>>
>>
>> spike
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20230420/0861c21f/attachment-0001.htm>