Re: personal AI

You wrote:

> The interviewer asked him what the rise of AI meant for the Church's
> understanding of human nature, and whether humanity's unique position as
> the "pride of creation" might eventually be challenged.


I asked Google's Gemini (ex-Bard) the same question. The text below was its
response:

The rise of AI is sure to spark interesting discussions within the Catholic
Church about human nature and our place in creation. Here's how it might
play out:

*Challenge to Human Uniqueness:*

   - *Loss of "Pride of Creation" Title?* AI surpassing human intelligence
   could threaten the notion of humans being God's "pride of creation." If
   machines become more capable, faster learners, and even possess a form of
   artificial consciousness, our unique position might seem less secure.

*Redefining Human Nature:*

   - *Focus on the Soul:* The Church might emphasize the embodied soul as
   the true differentiator. AI, lacking a physical body, wouldn't possess a
   soul in the Catholic view. This reinforces the importance of our physical
   existence intertwined with the spiritual.
   - *More Than Intelligence:* Catholicism emphasizes reason but also
   highlights human aspects like emotions, morality, and free will. AI
   struggling with these areas could solidify the idea that humans are more
   than just intelligent beings.

*Opportunities for the Church:*

   - *Reinforcing Human Purpose:* Questions about a "good life" in the face
   of advanced AI might lead people to seek answers in the Church's teachings
   on faith, meaning, and the importance of human connection.
   - *Ethical Guidance:* The Church can be a voice for responsible AI
   development, ensuring technology serves humanity and aligns with Catholic
   values.

*Uncertainties Remain:*

   - *Defining AI "Consciousness":* If AI develops a form of consciousness,
   the lines blur. The Church might need to grapple with the ethical
   implications and how it fits with their view of the soul.

*Overall:*

While AI's rise might challenge the idea of humans as the pinnacle of
creation, it could also lead to a deeper understanding of what makes us
truly human. The Church can play a role in navigating these changes by
emphasizing the importance of the soul, human purpose, and ethical
considerations in AI development.

On Fri, May 3, 2024 at 2:04 PM Markus Sabadello <markus@danubetech.com>
wrote:

> The therapist example triggered an interesting experience I recently had.
>
> I watched an interview on the topic of AI with the Archbishop of Vienna, a
> cardinal of the Catholic Church.
> The interviewer asked him what the rise of AI meant for the Church's
> understanding of human nature, and whether humanity's unique position as
> the "pride of creation" might eventually be challenged.
> The cardinal's answer was similar to the messages in this thread, i.e.
> even if AI becomes so good that it's indistinguishable from humans in an
> interaction, it will never itself "be human", feel empathy, love, fear, etc.
>
> But then later in the interview he admitted that some of his priests use
> AI for writing their sermons, and that he thought it was okay to do that
> "on occasion" :)
>
> Similar to the question of the social implications of interacting with
> "personal" AIs that represent human beings: What might be the implications
> of "divine" AIs trained with data sets from holy scriptures, word of God,
> that sort of thing? Scary? Or no problem as long as you "know" what's
> behind it?
>
> Markus
> On 4/29/24 11:21, Daniel Hardman wrote:
>
> I feel like we are not yet pondering deeply enough how an AI alters the
> social texture of an interaction. What is an AI's social and emotional
> intelligence, not just its ability to get work done -- and what is the
> social and emotional intelligence of us ordinary humans, vis-a-vis these
> tools?
>
> Per se, an AI has no human rights and triggers no social obligations on
> the part of those who interact with it. If I hang up the phone on an AI, or
> never respond to their messages, I don't believe I am being rude. And an AI
> has no right to privacy, no right to a fair trial, cannot be the victim of
> doxxing, etc.
>
> However, associating an AI strongly with a human that it represents
> introduces a social quandry that has never existed before, which is how to
> impute rights to the AI because of its association with a human. True, the
> AI has no standing in the social contract that would lead one to respond to
> its messages -- but if that AI represents a real human being, it is in fact
> the human being we are ignoring, not just the AI that does the human's
> bidding.
>
> Is lying to an AI that does Alice's bidding ethically the same as lying to
> Alice herself? Would it depend on the degree and intent of the AI's
> empowerment? What if Alice terminates her relationship with the AI -- does
> the grievance stay with Alice or with the AI?
>
> If I am a therapist who happens to have a really fabulous AI that can
> conduct remote therapy sessions over chat, is it ethical for me to go on
> vacation and leave my AI to counsel people about their deepest personal
> sorrows and perplexities, without telling them -- even if they can't tell
> the difference?
>
> I believe human beings have the right to know whether they are interacting
> with other human beings directly, or merely with a piece of technology
> that's doing another human's bidding and can pass the Turing test. This
> allows interpersonal and social judgments that are crucial to how we get
> along with one another. I am excited about the good that AI can do, and
> about the prospect of personal AIs, but I am categorically opposed to
> hiding the difference between people and AIs. The difference is real, and
> it matters profoundly.
>
> Alan said:
> > Do we ask for proof of humanity of other software running on behalf of a
> person?  What if a personal AI carries out its task using an application?
> Isn't the human who determines what the software, AI or otherwise, supposed
> to do the responsible party?
>
> Adrian said:
> >The group could not think of a single reason to make a distinction
> between me and an AI that I control as my delegate. To introduce such a
> "CAPTCHA on steroids" is to limit technological enhancement to corporations
> and "others". Will we treat personal technological enhancement the way we
> treat doping in sports? Who would benefit from imposing such a restriction
> on technological enhancement? How would we interpret the human right of
> Freedom of Association and Assembly (Article 20) to exclude open source
> communities creating open source personal AI that an individual can take
> responsibility for? Certifying the vendor, provenance, and training data of
> a personal AI seems like the last thing we would want to do. I hope what
> Drummond is suggesting applies to AI that is not transparent and controlled
> by an individual or a community of individuals in a transparent way. How do
> we see a world where two kinds of AI, personal and "certified" interact?
>
> Drummond said:
> > Manu has a good point. I have no problem interacting with an AI bot as
> long as I can be sure it’s an AI bot—and ideally if I can check its vendor,
> provenance, trained data sets, etc.
>
> Manu said:
> > Another interesting aspect here is that "the bots" are, probably
> within the next decade, going to legitimately exceed the level of
> expertise of 99.9% of the population on most subjects that could be
> discussed in an online forum. I, for one, welcome our new robot troll
> overlords. :P
>
>>