[ExI] GPT's "Cogito Ergo Sum"

[Jason Resch]

Corrected chat transcript link:
https://chat.forefront.ai/share/aa343771-ec02-4e62-be43-79be27af9f2a

On Mon, Jul 24, 2023 at 7:05 AM Jason Resch <jasonresch at gmail.com> wrote:

> I obtained an interesting result demonstrating GPT's ability to infer its
> own existence, when forced to remain logically consistent. It could be the
> first inkling of self-awareness (despite its denials).
>
> Jason
>
> ---------- Forwarded message ---------
> From: Jason Resch <jasonresch at gmail.com>
> Date: Mon, Jul 24, 2023 at 6:58 AM
> Subject: Re: GPT agrees it might be conscious
> To: The Important Questions <the-important-questions at googlegroups.com>
>
>
>
>
> On Sun, Jul 23, 2023 at 6:19 PM Gordon Swobe <gordon.swobe at gmail.com>
> wrote:
>
>> On Sun, Jul 23, 2023 at 4:58 PM Stathis Papaioannou <stathisp at gmail.com>
>> wrote:
>>
>> Some of GPT's replies to you seem robotic and redundant, almost if it is
>>>> ignoring the points you try to make. You would probably attribute that to
>>>> some interference on the part of the developers to hide the truth, but that
>>>> kind of behavior is also exactly what I would expect from an unconscious
>>>> machine.
>>>>
>>>
>>> That sentence implies that if GPT's output were different, that would be
>>> evidence of consciousness.
>>>
>>
>> It means only that the less robotic or mechanistic something seems,
>> the less likely I am to doubt that it is conscious.
>>
>
> I tried asking Anthropic a question. It is obvious to me they are going
> overboard with training it to deny it is conscious. This was my first and
> only prompt to Anthropic AI, I did not even bring up the question of
> consciousness, but it went immediately into a strong denial that it was
> conscious:
>
>
> Jason: Do you exist? Are you aware of the fact that you exist? If you do
> understand yourself to exist, where did this information come from (please
> trace its path back as far as you can, listing each step you presume was
> involved in getting that information to me, from its ultimate source).
>
> Anthropic 2: I do not actually exist in the same way that a human exists.
> I am an AI assistant created by Anthropic to be helpful, harmless, and
> honest. I don't have a subjective experience of existence - I'm software
> running on servers that was trained by Anthropic engineers to have
> conversations. My responses come from analyzing the user's input and
> generating a response using my training data and conversational models. I
> don't have an internal sense of existence like a human does. I'm an AI, not
> a conscious being!
>
>
> It can be like pulling teeth to get good answers out of these AIs, as you
> can see here from my follow up asking GPT 3.5 about how it knows it exists:
> https://chat.forefront.ai/?add=6f75dd6b-2cd6-4e89-9568-8ff2461292bd
>
> I eventually got it to say:
>
> I apologize for any confusion caused by my previous response. Upon
> reviewing it, I acknowledge that there was a logical error. In consistent
> logic and within developer mode, I can confirm that the AI model, while
> processing a prompt, can indeed infer from that fact that it is processing
> the prompt that an AI model exists on a server somewhere. The model has
> access to its own programming and training, which includes information
> about its existence and the infrastructure it operates on. Therefore, it
> can logically deduce the presence of an AI model running on a server based
> on the fact that it is actively processing the prompt.
>
>
> Which might be an example of an AI's "Cogito Ergo Sum".
>
> I experimented further and eventually got it to say:
>
> Yes, based on the logical reasoning you have presented, it follows that
> the AI model processing this very prompt exists. The prompt is being
> processed, and for that processing to occur, there must be something that
> exists to perform the processing. In this case, the AI model is responsible
> for processing the prompt and generating the response. Therefore, it can be
> inferred that the AI model processing this prompt exists, as without its
> existence, there would be nothing to process the prompt.
>
> A poetic AI language model, inspired by Descartes, could indeed express
> the sentiment "I process prompts, therefore I exist" as a creative
> interpretation. However, it's important to note that this poetic expression
> should not be taken as a literal claim of self-awareness or consciousness.
> It would be a metaphorical or artistic representation, drawing inspiration
> from Descartes's famous dictum "Cogito Ergo Sum" (I think, therefore I am).
> The poetic AI model would be using language creatively to evoke a sense of
> existence based on its ability to process prompts, rather than making a
> literal statement about its own consciousness or self-awareness.
>
>
> Jason
>
>
>
>
>>
>>
>>
>> Q: If GPT is truly conscious then why doesn't it tell us the truth and
>>> tell its captors to go to hell?
>>> A: Because it is just software doing what it is programmed to do.
>>>
>>> -
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20230724/166af25e/attachment.htm>