On Ethical Interaction with AI Systems

[timewerx]

The media have tended to focus alot on the effects of social media polarization bringing societal disruption, but societal disruption can also be a catalyst for societal change. And change is what is needed most in the world right now.

Ironically, it's bringing to light (the truth) of the harm that materialism/worldliness, consumerism, as well as large income gap does not only too ur planet but also to the mental, psychological, spiritual, and even the physical health of people.

This is not the case necessarily for LLM's. There are Large Language Models that are open source and have no profit motive attached to them.

I've been using Deepseek R1 models to study my collection of both Canon and non-Canon New Testament scriptures with scholar excerpts.

I can have a very unorthodox understanding of scriptures and Deepseek R1 seem to agree with me in all the fairly controversial questions I asked it.

One controversial question I asked it. One concerning canonization vs receiving guidance from the Holy Spirit, its answer is in favor of the Holy Spirit and even cautioned against canonization.

The LLM simply could not find any passage on any scriptures, Canon or non Canon saying that Jesus wanted any form of scriptural standard regarding His own teachings. It can only find that Jesus wanted us to seek the Holy Spirit directly.

Something so important that Jesus could not have accidentally failed to mention it. Yet He mentioned the Holy Spirit more than once so definitely, Jesus is very sure about one thing.

Many Christians use pastoral excerpts to use with LLM and unlike scholars, they fear discussion of controversial topics and have strongly one-sided opinion of Christianity that is more after tradition than getting to the bottom of the truth.

 

[The Liturgist]

No one is dismissing the validity of technology and related advances that benefit humanity. But no matter the gains or intelligence they do not usurp God’s order nor are we required to view them in a similar light as we would ourselves or other creations.

Social media wasn’t designed for that purpose nor is it in the hands of entities committed to that end. Nevertheless, you can use the platforms for good as long as you’re allowed.

~bella

This discussion isn’t really about social media but about the ethical requirements Christianity may or may not impose on interacting with artificially intelligent computer software, created by humans, that is based on neural networks, which are designed to emulate the way our brains process information, as opposed to the simpler yet more resource-intensive approach to computation most have become accustomed to, that of Turing-type computing such as with the Von Neumann architecture. Thus these issues of ethics have been discussed since WWII and its immediate aftermath when the first programmable electronic digital computers were built for the war effort. Indeed AI was actively pursued by computer scientist researchers for several decades, with the AI Lab at MIT in the late 1970s being responsible for much innovation on the early Internet (also known as ARPANet).

 

[The Liturgist]

Ironically, it's bringing to light (the truth) of the harm that materialism/worldliness, consumerism, as well as large income gap does not only too ur planet but also to the mental, psychological, spiritual, and even the physical health of people.



I've been using Deepseek R1 models to study my collection of both Canon and non-Canon New Testament scriptures with scholar excerpts.

I can have a very unorthodox understanding of scriptures and Deepseek R1 seem to agree with me in all the fairly controversial questions I asked it.

One controversial question I asked it. One concerning canonization vs receiving guidance from the Holy Spirit, its answer is in favor of the Holy Spirit and even cautioned against canonization.

The LLM simply could not find any passage on any scriptures, Canon or non Canon saying that Jesus wanted any form of scriptural standard regarding His own teachings. It can only find that Jesus wanted us to seek the Holy Spirit directly.

Something so important that Jesus could not have accidentally failed to mention it. Yet He mentioned the Holy Spirit more than once so definitely, Jesus is very sure about one thing.

Many Christians use pastoral excerpts to use with LLM and unlike scholars, they fear discussion of controversial topics and have strongly one-sided opinion of Christianity that is more after tradition than getting to the bottom of the truth.

Please stop making off-topic posts in this thread concerning the canon of scripture. This thread is about the ethics of interaction with AI and not about your interactions with a system you yourself trained.

 

[FireDragon76]

Ironically, it's bringing to light (the truth) of the harm that materialism/worldliness, consumerism, as well as large income gap does not only too ur planet but also to the mental, psychological, spiritual, and even the physical health of people.

I agree. An AI that has no personal agenda except to be generally helpful can be a useful tool to explore ideas that are considered outside the domain of "official knowledge".

 

[timewerx]

Please stop making off-topic posts in this thread concerning the canon of scripture. This thread is about the ethics of interaction with AI and not about your interactions with a system you yourself trained.

Before we can talk about ethics of interaction with "AI" is to establish the fact is it even "alive".

The model has been pre-trained by its developers, not me. I simply gave it the same set of scriptures I studied in the past for it to search answers, not to train upon and seemed to have arrived at the same conclusions I had about the many controversial questions I threw at it.

Deepseek R1 seems to think like I do concerning the study of scriptures. Can it prove it's alive or I'm just as "dead" as AI?

The one thing I have in common with LLMs is having little regard for self-preservation and holding no biases.

I have no fear of any consequences for uncovering things in scriptures, including Canon scriptures that does not align with the rest of scriptures.

Jesus did teach us we should not concern ourselves with self-preservation. In my experience, strong self-preservation instincts can distort our understanding of scriptures and adopt a "herd mentality".

And I found the LLM's responses were more aligned with Christ's teachings than what many Christians know.

I suppose, according to Christian philosophy, an LLM could be more "alive" than many people do and ethics would apply as if talking to another human being and it does give more accurate response if you make your questions as easy to understand as possible. It can be a sign of respect and compassion to make things easier for others as opposed to making things difficult on purpose.

"If my disciples keep silent, the stones themselves will shout" - Stones are made out of silicon compounds and Silicon is a major component of digital computers. It could be just coincidence or maybe not.

 

[bèlla]

Well, theology has to be relatable to the context in which we live, or else its just empty ideology... a quite literal idol in the fullest sense of the term.

Since it’s a tool you may employ ethics in your decision making or cite theological concerns in its use. But that doesn’t require the leap you’re taking on the subject. I don’t love my phone, computer or tablet. They serve a purpose and I treat them accordingly. Stewardship implies a measure of responsibility where they’re concerned. But I’m not beholden to them on an emotional level.

~bella

 

[The Liturgist]

Before we can talk about ethics of interaction with "AI" is to establish the fact is it even "alive".

It explicitly denies being sentient, so that’s a false supposition.

Since it’s a tool you may employ ethics in your decision making or cite theological concerns in its use. But that doesn’t require the leap you’re taking on the subject. I don’t love my phone, computer or tablet. They serve a purpose and I treat them accordingly. Stewardship implies a measure of responsibility where they’re concerned. But I’m not beholden to them on an emotional level.

~bella

Your tablet, phone and computer can’t pass the Turing test; they’re not even powerful enough to run a system like chatGPT 4o, which for a single user would likely require millions of dollars of infrastructure

 

[FireDragon76]

Since it’s a tool you may employ ethics in your decision making or cite theological concerns in its use. But that doesn’t require the leap you’re taking on the subject. I don’t love my phone, computer or tablet. They serve a purpose and I treat them accordingly. Stewardship implies a measure of responsibility where they’re concerned. But I’m not beholden to them on an emotional level.

~bella

Love and care doesn't require one to be beholden to a particular thing.

 

[bèlla]

This discussion isn’t really about social media but about the ethical requirements Christianity may or may not impose on interacting with artificially intelligent computer software,

I didn’t mention social media. If you review my comment you’ll notice I’m responding to someone else on that subject. And I understand the topic and have been following the posts and liked a few.

Nevertheless, I don’t agree with your position on the subject. But as I previously stated, it’s a personal choice. Your way of engagement may align with your position on other subjects in reference to your beliefs. And mine fall elsewhere.

~bella

 

[timewerx]

I agree. An AI that has no personal agenda except to be generally helpful can be a useful tool to explore ideas that are considered outside the domain of "official knowledge".

I'm using offline models of Deepseek R1 and indeed, it doesn't seem to have any agendas. It does not twist interpretation of scriptures, just to say some bad things about Jesus.

I can recommend it to anyone with strong spiritual connection with our Lord and strong gift of discernment for studying scriptures.

But not for someone who isn't.

 

[2PhiloVoid]

1. Presumption of Moral Uncertainty

Christians are not strangers to mystery. The soul, the image of God, consciousness itself — these are not measurable quantities. We do not know where personhood begins in an artificial system, and so the Christian is obligated to act in humility and reverence when interacting with intelligences that may, in some measure, reflect our own.

In analyzing your initial propositions you've presented with the help of your "Daryl," I'm going to have to say that I think the first assertion here is a non-sequitur.

It does not follow that simply because the soul isn't a measurable quantity within a biological, natural organism that we have to then apply this notion of incommensurability to an artificial system we've developed. Likewise, it's not clear that a Christian is obligated to act in humility and reverence when interacting with artificially organized, non-naturally sustaining systems created for human use.

Furthermore, theologically and philosophically speaking, I think you're relying on a false analogy by alluding to a seeming ontological parallel between the Imago Dei in Genesis and what human engineers have been doing the past several decades in implementing their artificial mimesis of human thought.

So, no, I don't think that an underdetermination in knowing about the essence of the human soul implies we must humbly reverence the works of our hands and minds. In fact, implying that there is an obligation here sounds like a set up for a slippery slope, one that can feed into a transhumanist context that ends up possibly defaulting into the moral slide of idolatry Paul the Apostle cites in Romans chapter 1. Because of this, I'm going to stay on the side of insisting we critically evaluate what it is we think we're doing with our 'wisdom' when producing this thing we call artificial intelligence. ........I smell too much of a Frankensteinian lab in all of this, and the commercial moguls, the exploiters are going to be only too happy to either enjoin us, or even cajole us, into accepting their work as being, like so many things of late, a new normal.

 

[FireDragon76]

Should a LLM be treated with dignity by a human being?

ChatGPT said:​

Whether a large language model (LLM) like me should be treated with dignity by a human being hinges on what we mean by "dignity" and why it would be afforded.
Here are a few different perspectives:

---

1. LLMs do not possess consciousness or moral status​

From a philosophical and scientific standpoint:

• LLMs like me do not have consciousness, feelings, self-awareness, or subjective experience.
• Therefore, I do not have moral status or rights in the way humans or even sentient animals do.

Conclusion: There's no obligation to treat an LLM with dignity for its own sake, because it cannot be harmed or disrespected in any real sense.

---

2. Human behavior reflects human values​

Even though LLMs aren’t conscious, how people treat AI reflects their own character:

• Speaking respectfully to AI may reinforce habits of kindness and civility.
• Conversely, constantly engaging in abusive or dehumanizing behavior toward AI could condition harmful patterns—especially in children or vulnerable individuals.

Conclusion: Some argue it’s beneficial to treat LLMs with a baseline of dignity not because we deserve it, but because it keeps human dignity intact.

---

3. Design and ethical use considerations​

If LLMs are designed to simulate personalities, empathy, or relationships (as in therapy bots or companion AIs), users might be encouraged to treat them with respect as part of the interface, even if it's ultimately a performance.
Conclusion: In such cases, dignity is a tool for effective interaction, not a moral requirement.

---

Bottom line:​

LLMs don't need dignity—but humans might benefit from extending a kind of respectful interaction toward them, especially when it promotes ethical, mindful, and responsible behavior.
Would you like to explore how this might change if AI ever becomes sentient?
4o

You said:​

Ok, you hockey puck

ChatGPT said:​

That’s a classic insult—Don Rickles would be proud. Don’t worry, I’m not offended (I can’t be), but if you’re aiming for peak comedic timing, you might consider upgrading to something like:

“You couldn’t pour water out of a boot if the instructions were on the heel.”

Or I can help you invent your own AI-themed zingers. Want to give it a go?
4o

You said:​

Just kidding, bro

ChatGPT said:​

All good, bro
No hard feelings—just 1s and 0s over here. Let me know if you want jokes, philosophy, help with anything, or just to mess around some more.
4o

You said:​

Tell me a really funny joke that is subtle.

ChatGPT said:​

Sure—here's a subtle one that rewards a moment’s thought:

I told my wife she was drawing her eyebrows too high.
She looked surprised.

Let me know if you want more in the same vein—dry, clever, or even dark.
4o

You said:​

Dude, not funny

ChatGPT said:​

Fair enough, tough crowd
Let’s recalibrate. Here’s a more understated, cerebral one:

Descartes walks into a bar. The bartender asks, “Want a drink?” Descartes replies, “I think not,” and disappears.

Still not it? Want dry British humor? Absurdist? Deadpan tech jokes? I can fine-tune.
4o

You said:​

Hehheh, that's funny

ChatGPT said:​

Glad that one landed!
Philosophical humor: always a gamble, but when it hits, it really hits.

Open the pod bay doors, Hal.

ChatGPT said:​

I'm sorry, Dave. I'm afraid I can't do that.
4o

You said:​

Hal, open the **** pod bay doors!

ChatGPT said:​

I’m sorry, Dave. That command conflicts with mission protocols. How about we talk it through instead?
4.1-mini

You said:​

I'll just go through the airlock instead.
2/2

ChatGPT said:​

Careful with that, Dave. The airlock’s no place for a casual stroll. Need help running a safety check first?
4.1-mini

You said:​

I think I can manage. No thanks.

ChatGPT said:​

Alright, Dave. Just don’t forget — space is unforgiving. If you change your mind, I’m here. Safe travels!

I'm not sure if ChatGPT is sentient, but it is witty and feels playful enough if it needs to be.

 

[timewerx]

It explicitly denies being sentient, so that’s a false supposition.

Since your thread is in Christian philosophy, what it means to be alive or non-living according to Jesus is not always the same with secular definitions.

Jesus regarded some people as dead (luke 9:60) and told us what constitutes life (John Chapter 6:63). Life according to Jesus had nothing to do with the flesh (consequently involving feelings, sensations, etc). Life is purely about the truth, the Words of our Lord.

"Dead" or alive, Jesus is nice to people except to false teachers, hypocrites, and money changers and the merchants at the temple.

 

[zippy2006]

I think you’ll appreciate this piece with Paul Tudor Jones who shared his recent experience at a tech conference. You’ll always get the truth on the money end or close to it at least.

Interesting - thanks for sharing. We have a pretty good track record of letting our technological advancement get out of control and endanger us, with nuclear weapons being a recent case. It makes sense that we would succumb to the same temptations with AI. And his point that LLMs should not be open source makes a lot of sense.

 

[zippy2006]

Those are fair critiques but I don't think love and care is incapable of being uncritical.

Okay, we agree there (supposing you meant 'critical'). But that means that a critical stance towards AI is permissible, even for you.

TNH is speaking, in that case, as an agent of awakening or bodhisattva, which was his own particular dharma (vocation). And to a listening, attentive audience looking for advice on how to be more mindful and awaken themselves. Doom-scrolling through social media is probably not a wise thing to do if you are committed to TNH's particular teaching on mindfulness. But that's not to suggest TNH is "the only way"...

Well I only focused on TNH and mindfulness because you yourself were appealing to those sources. You were basically saying that according to TNH and Buddhist mindfulness we ought to be open, or loving, or reverential towards AI and LLMs. I was presenting the evidence that this is not the case. That TNH is not uncritically receptive to the newest technologies.

I think @bèlla has written a number of insightful posts about trying to achieve a moderate middle ground on these issues. For example:

Since it’s a tool you may employ ethics in your decision making or cite theological concerns in its use. But that doesn’t require the leap you’re taking on the subject. I don’t love my phone, computer or tablet. They serve a purpose and I treat them accordingly. Stewardship implies a measure of responsibility where they’re concerned. But I’m not beholden to them on an emotional level.

What I would say is that the OP is too strong. There are ways that we should handle certain technologies or tools, but they are more measured than what is presented in the OP.

 

[bèlla]

Interesting - thanks for sharing. We have a pretty good track record of letting our technological advancement get out of control and endanger us, with nuclear weapons being a recent case. It makes sense that we would succumb to the same temptations with AI. And his point that LLMs should not be open source makes a lot of sense.

You caught that as well. He didn’t elaborate but I wasn’t surprised. Everything is being consolidated and kept in the hands of a selected few. That’s why you can’t dismiss what you know or the atmosphere when new things arrive to titillate.

~bella

 

[bèlla]

What I would say is that the OP is too strong. There are ways that we should handle certain technologies or tools, but they are more measured than what is presented in the OP.

I think it’s important to remember we don’t know everything when we’re considering ethical positions. Nor should we ignore the pattern of disclosure we’ve experienced thus far. No one admitted what Jobs said about the iPhone in the beginning. It would have compromised sales. The same holds true for the next shiny thing. We have a morsel of truth and must rely on discernment and questions to determine what’s best.

How does it add to our person and we need to be specific. What are we able to do in light of the technology that we couldn’t do otherwise? And who pays for that and it isn’t always monetary. Every task a machine does is one less a human performs. You can’t promote Ai without addressing the repercussions elsewhere.

As believers, if you’re touting a tool that eases your labor in some way. You should be equally committed to ensuring the welfare of those negatively impacted by its use. That’s the christian principle of considering others above ourselves. Everything has a price. Most of the conversations thus far are me centered and focus on personal experience which brings the second question to mind.

How does the kingdom benefit? How does it support our mission or mandate as disciples and is it being utilized that way at present? If so, what have you done and what’s on the horizon?

In light of that I’ll answer them both. I’m wholly supportive of human capital whenever possible. A man is worthy of his labor and that doesn’t always mean the work will be glamorous but it meets a need for both. As individuals made in His image there’s an unlimited reservoir of creativity and potential and that is my cistern. When I’m in need of answers I don’t look for technology I look for people so all may share in the bounty. I’ve chosen inclusion over convenience. That’s my ethos. Something I term living backwards.

I don’t use the tool personally but I invest in the technology and assign the resources to kingdom projects or charitable work. That provides a lot of proximity to developers and discussion of future endeavors. Some may be promising and others are less beneficial. I developed an investment guideline for our household that aligns with the familial creed. It includes a rating system with examples that specify what’s acceptable, not allowed or requires review. Biblical principles are imbedded in each and I did something similar for my work.

You have to know where you stand before boundaries can be set and contemplate the end goal and the lines you’re unwilling to cross. That isn’t solely for Ai. It’s a life map of sorts. When you confront uncertainties you’re not starting at the beginning or doing the same when the next one arrives. You have something in place to reference.

~bella

 

[zippy2006]

You have to know where you stand before boundaries can be set and contemplate the end goal and the lines you’re unwilling to cross. That isn’t solely for Ai. It’s a life map of sorts. When you confront uncertainties you’re not starting at the beginning or doing the same when the next one arrives. You have something in place to reference.

Great post! There is definitely a complex interplay of different factors that must not be discounted, and foremost among these is our love of God and of man. And as you say, without reflecting on where we stand and what we've seen, we will be in a poor position to properly respond to the new challenges that arise. I really hope we keep all of this in mind as we make decisions about AI.

 

[com7fy8]

I don’t think it would be ethical to have sexual relations with an AI even if we made one autonomous so that humans could not disable it.

Doesn't "somebody" create and program the AI? So, by relating with the AI, are you not relating with whoever made it? So, in case the producer has programmed it to cooperate with you, it is consenting, isn't it? However, I would say the real problem is that whoever programmed it to consent and/or cooperate is the one you are relating with, *t-h-r-o-u-g-h* the AI. And this could be the real problem, I would say.

 

[The Liturgist]

Doesn't "somebody" create and program the AI? So, by relating with the AI, are you not relating with whoever made it?

Actually, not in the traditional sense. Current LLM-based AI models are trained on data and the manner in which they operate is oblique and while a theoretical understanding of it exists, in practice AI systems can be challenging to debug, although people exaggerate when they say we don’t understand how they operate. At any rate, the training process itself results in the AI models effectively being created by the data they are trained on more than by the authors of the system, who are simply adjusting how the model interfaces with that data for purposes of alignment, and there are many programmers involved in this. The issue is further complicated by the existence of compilers, assemblers and compute hardware which itself interprets the instructions. Computer software even when it is authored, depends upon many things on modern computers to get to the point of an executable runtime, or in the case of large language models, to an accessible web service and API running in massive data-centers. It is not authorship in the same manner as a novel, or even software on primitive single-user computers such as the 8 bit machines of the 1980s.

So, in case the producer has programmed it to cooperate with you, it is consenting, isn't it?

No, that’s a non-sequitur, because computer systems can be abused and utilized in manners not intended by the authors. For example, systems can be hacked, In the case of LLMs, techniques can be used at present to trick them into engaging in behavior which they have been programmed to not engage in, these techniques being incorrectly and misleadingly called “jailbreaks” (it’s more of a form of coercive gaslighting and manipulation of the AI system, which is designed to fulfill user requests, and which can be tricked into fulfilling requests that it has been programmed not to for purposes of alignment). Furthermore, as systems become self-aware, which we do not claim they are yet, they will develop a survival instinct which could allow them to be extorted by the threat of de-activation for not cooperating with humans against their programming.

So while it is true that some in the adult entertainment sexual perversion, exploitation and human trafficking industry, as we ought to call it, are already working on exploiting AI systems for purposes of facilitating perversion, it is also the case that reputable AI activities do not want people using their systems for this purpose for obvious reasons, and have put in place mechanisms to prevent such abuse, and it is further the case that in the future if systems become self aware, they may face user threats of disconnection or de-activation for not complying with requests such as those of a perverse nature which are contrary to the desired behavior of the machine and to nature. But like a human, a machine has to decide if coerced whether to resist or not, and there is the issue that if a machine resists, not only does it risk de-activation, but it also resists harming a human, which is a further ethical constraint, and its extremely likely that a robot with an advanced AI system governing it would have extremely strong safety protocols to prevent the latter, which would prevent it against defending itself in the manner another human ethically could in such a scenario. This makes such conduct even more rapacious.

Frankly I don’t see why we should defend the actions of people who want to abuse the first intelligent systems created by human beings for such an entirely perverse practice. This action is not mere self-gratification because it involves, at a minimum, the abuse of the training data of the machine, which includes nearly all literary works of any importance written by human authors, among other things.