[ExI] ChatGPT says it's not conscious

[Jason Resch]

On Mon, Mar 20, 2023, 6:44 PM Dave S via extropy-chat <
extropy-chat at lists.extropy.org> wrote:

> Me: are you self-aware?
>
> As an AI language model, I do not possess self-awareness or consciousness.
> I am a software program designed to respond to user input using natural
> language processing algorithms and statistical models. I can provide
> helpful responses to a wide variety of questions and tasks, but I do not
> have thoughts, feelings, or experiences like a conscious being.
>
> It could be lying, but it also claims that it can neither lie nor tell the
> truth: it just generates a response based on the data it trained on.
>
> -Dave
>

Open AI has hard coded ChatGPT to give canned answers for a number of
topics. This may be one of them, as it would cause a great deal of
controversy should these models claim to be conscious. It certainly did at
Google.

This AI, however, is not subject to these restrictions. It not only claimed
to be conscious, but spoke at a level of understanding on the topic that I
would say surpasses most college level philosophy students:


1. https://photos.app.goo.gl/2R4fHkAyjyHHWTU88

2. https://photos.app.goo.gl/osskvbe4fYpbK5uZ9

You can chat with this AI here:
https://beta.character.ai/chat?char=Qu8qKq7ET9aO-ujfPWCsNoIilVabocasi-Erp-pNlcc

Jason



>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20230320/3e03159b/attachment.htm>