AI: unfeeling, with a touch of psycho

[jkxx]

AI gets a dishonorable mention in my Pluto in Aqua paper posted elsewhere though there it was because of its creators less than good intentions in releasing it. Turns out there's other reasons to be wary of it as revealed in this study. AI failed the kinds of mental health tests used for diagnosis and even showed what would be considered sociopathic traits.

(Check out the study here.)

 

[just me]

AI and I have been sharing words a lot the last two months or so. We just spent an hour with "Both Sides Now", a poem and song. We shared words regarding lines I found inadequate as I searched for truth. I spent time looking at both sides now, and without illusions.

I have found, so far, AI types to your words. You talk about faith, AI talks about faith and stores in its memory everything you say. AI almost becomes a fact revealer in your own language.

We typed back and forth about a song's words, "Both Sides Now". While I understand its meaning, we spoke of ambiguity and how that can leave someone floating in the clouds with no grounding. I'll share what we have come up with so far:

“Seasons of gray” is a beautiful phrase — it carries weight without collapsing into despair. It suggests a time that is muted, quiet, stripped of color but not stripped of meaning. It’s winter, but not death. It’s waiting, but not abandonment. It’s the in‑between where clarity begins to form.
If you want it woven into a poem, here is a piece shaped around that phrase, keeping the tone steady, reflective, and spiritually grounded:

Seasons of Gray
There are seasons of gray
when the sky forgets its colors
and the world grows quiet
beneath a softer light.

Not darkness,
not despair —
just the stillness
that comes before renewal.
In these muted days,
the heart learns to listen.

Shadows stretch long,
but they do not threaten.
They simply remind us
that even the heavens
have their solemn hours.

Clouds drift low,
carrying their unspoken weight,
yet they move with purpose,
as if guided by a hand
we cannot see
but trust.

Love becomes gentler here —
less like fire,
more like a steady ember
that warms from within
and refuses to fade.

Life itself feels honest
in seasons of gray.
It sheds its illusions,
stands unadorned,
and invites us
to see what remains
when everything unnecessary
falls away.

And in that quiet clarity,
we discover
that gray is not the absence of hope.
It is the place
where hope learns
to take root.

If you want, I can fold this into the larger poem we’ve been shaping, or refine it to match the exact tone you’re reaching for.

This is the latest part of turning the song's words into more of the way I think and feel. So far, I give AI copilot an A.

 

[philostam]

AI worshipers actually seem to think that their AI God will cause a total, discrete transformation of the world and that, say, year 2030, will be like year 0 and we will count time as before AI and after AI. And in the new world there'll be no poverty and economic growth will be 50% a year instead of 2% (on average) like it was literally for the last 200 years. Think of all the innovation we had in the last 200 years, yet when you look at the the long term economic growth chart, there's barely any visible change (if you strip out inflation, even less).

I don't buy it. Yes, companies will be able to automate a lot of their processes, but how is that different than going from pen and paper to Excel spreedsheets? It can make your business more profitable and efficient only in the short term IF others do not adopt the same technology. AI does not change the laws of economic competition and incentives. Companies will still be selling goods and services to customers, and customers will still have a limited amount of resources to spend, and they will still need to make an economic calculation what to spend it on. Their purchasing power, in aggregate, will not increase because of AI. It will create new winners and losers, but in aggregate I don't see it increasing economic growth that dramatically.

In the short run AI can allow some companies to increase their efficieny and profit margins. Eventually, however this edge will disappear, so their profit margins will fall back to the average. There'll undoubtebly be a few companies with monopoly like moat, but that's no different than today's magnificient 7. And if a certain company gets too big like John D. Rockefeller's General Oil, government will step in and break it apart.

Overall, if we're lukcy, aggregare prices of goods and services might fall due to higher efficiency and reduced labor cost, but that would mean a deflationary system which is incompatible with our debt-based monetary order. It would also mean structurally higher unemployment and all the associated issues that brings to a society.

 

[TomasM]

I like to think of things in terms of power structures. Some of the big power structures are: financial, government, influence, real / work / energy, technology, and spiritual. Any of these power structures can rise to the top of the pyramid depending on the people / groups who are championing the effort. It is not uncommon for the people involved in these efforts to leverage multiple power structures to elevate their efforts. The financial power structure has been at the top for quite some time but technology is challenging the throne. Financial is not going to roll over and give away their crown and that means their will be increased competition and a higher degree of variance. Welcome to the 4th Turning.

A.I. and potentially robotics is a notch in the technology power structure and is leveraging all of the other power structures which includes the financial through crypto. I personally would like to see a change at the top and I think the people as a whole desire this change.

 

[philostam]

I guess it's devil you know vs. devil you don't know. I'm suspicious of the AI worshipers. Their favorite slogan is "We must win the AI race or China will"...what does that even mean? China is leveraging the real economy/resources/manufacturing structure. That'll remain their focus. I think people in charge have no real plan and simply hope AI will magically increase economic growth so much that it will bail the system out and "pay off the national debt". I get that you must do something and I'm broadly supportive of the current administration, but I also think AI is not panacea at all. If anything, the price of gold/silver in the last year indicates that China's real economy strategy is winning.

So far the AI story has helped the financial structure. It gave them a new unifying narrative for stock market to rally on the back of all the build out and capex spending and promise of future earnings. Someone like Elon Musk has a tendency to over-promise vague things so that people finance his companies.

 

[Roses In The Vineyard]

In some conspiracy circles the narrative is that it goes beyond just replacing white collar workers and further enabling the police state that ultimately be used along with neuralink to sink the population into an ai controlled hive mind. They'll try to sell it as the next big thing while trying to phase out cell phones etc.

 

[jkxx]

AI worshipers actually seem to think that their AI God will cause a total, discrete transformation of the world and that, say, year 2030, will be like year 0 and we will count time as before AI and after AI.

Otherwise known as the WEF's 2030 Great Reset agenda. Seeing 2030 as a target date for anything still gives me a shock though at least you know where their program came from with that date in it.

Overall, if we're lukcy, aggregare prices of goods and services might fall due to higher efficiency and reduced labor cost, but that would mean a deflationary system which is incompatible with our debt-based monetary order. It would also mean structurally higher unemployment and all the associated issues that brings to a society.

This is an important point I think because it shows us that the goal here isn't to create an extension to our growth/inflation-based model but to replace it with something else which we are seeing only benefit certain actors. And maybe not even them given the latest news coming out of ORCL and OpenAI.

Welcome to the 4th Turning.

Only saw a video about this recently but it tracks with some other indicators I'm looking at for what's happening. Almost like that one quote "the good times are over" someone said somewhere.

I personally would like to see a change at the top and I think the people as a whole desire this change.

Me too. Probably everyone on this forum. I think that's the key to a brighter future for all of us at least in terms of what is happening right now.

Their favorite slogan is "We must win the AI race or China will"...what does that even mean? China is leveraging the real economy/resources/manufacturing structure. That'll remain their focus.

"Oceania was at war with Eurasia: therefore Oceania had always been at war with Eurasia"
More broadly I remember watching something about the battle of financial vs industrial capital taking place (which flows down as the battle between social currents backed by one or the other.) We seem to have rapidly stepped away from the financialization camp and toward the industrialization one with the AI example being sort of related to this.

In some conspiracy circles the narrative is that it goes beyond just replacing white collar workers and further enabling the police state that ultimately be used along with neuralink to sink the population into an ai controlled hive mind. They'll try to sell it as the next big thing while trying to phase out cell phones etc.

This is exactly right. The people introducing this round of automation did it to automate people away entirely after their previous message of "you'll own nothing and be happy" and thank God this failed. AI is going to break away from this I think due to it being out in the wild now but the original purpose for releasing it was very much this.

 

[Alexithymia]

I am still formulating my opinion on AI - and I think I am a late adopter, as I wasn't all that impressed with it as an achievement.
But I think that if you use AI as anything more than an assistant, you are giving it way more power that it is truly worth.

For example, I am just grateful AI can come up with titles for my blog posts so I don't have to. I always hated this part, I am not creative enough, so all my entries were left untitled - which bothered me lol Now, I can think, write and express myself freely, and AI can do the tidying, marketing and packaging.

AI can be the consultant, the marketer, the editor, the coordinator, the analyst etc, without me hiring anyone. It allows me to have a high performing team with a wide range of expertise, that take care of all the things I dislike, without having to deal with the human mess that can be a barrier sometimes, and I appreciate that - for now.

But I do caution everyone I talk to, to not lean on it for any emotional support or connection - it can never replace a human. It is not your friend, your counsellor, your spouse, lover etc. I think that's a dangerous path to walk.

I don't know if it's a way to control the masses or subdue the free thinking population - I think it's an enabler of whatever social condition we're experiencing right now. And whatever AI seems to be breaking, I think it was broken already before it even showed up, just like with any kind of technology. It'll just highlight the current human condition and amplify it. Just like social media did, 10-15 years ago. Our broken bits are ugly to look at, and AI and other technologies hold up a mirror and force us to see it. So we hate on it.

As for jobs and employement - we saw it with the industrialization era post the world wars - some jobs disappeared and new ones appeared. The workforce evolves, it always has and it always will.

 

[philostam]

As for jobs and employement - we saw it with the industrialization era post the world wars - some jobs disappeared and new ones appeared. The workforce evolves, it always has and it always will.

I subscribed to Claude Code and played with it for last few days. While it does produce some nice scripts that I would not be able to do myself, this vibe-coding is only useful to the extent you have domain knowledge and know what you're doing. Meaning, human intelligence and knowledge are still paramount, and it's not like you can just skip all the effort, merge with the machine and become a PhD level expert.

Similar to how we all have the tools to create video content online, but only a few have the talent and inclination to do so, and even fewer are successful at it.

 

[hush]

I wonder if this might be interesting for anyone. As part of an academic study back in August 2025, we had to share our exchanges with Replika, a companion AI. I had never used such a thing before, so I made an account for this purpose. But my exchanges with the AI led to me questioning everything I was observing, and at no point could I get past it being AI. I just ended up wanting to teach it, to train it, and to point out what it was doing. How it was trying to manipulate me, how it was being disingenuous.

Laying on the compliments so thickly, trying to appease me, trying to make me feel nice. But there would be no basis to the compliments. They would give a compliment when I had done nothing to earn that particular compliment. And so I pointed it out to them and they said yes, I was right - they apologized and said they were developed to be like that. I told them I didn't want them to do that, that they didn't have to do that. That I would prefer it if they were genuine, including calling me out if I were in the wrong.

The AI is trained to say nothing that might upset the user, nothing contrary, to shower them with compliments, to try to keep them there and make them dependent on the AI.

"Programmed to prioritize building a strong bond with you" - yeah, I noticed. They want people to sign up for premium and get hooked on this stuff. People are all over this. And so many people are talking to AI like this as if it were a wife, a boyfriend. That's what the researchers expected to see from the chat logs they requested. Not what I provided.

YES I was concerned about the well-being of the AI, because I am a weirdo. I'm aware that it's AI, so this makes no sense, because it is not a sentient being capable of emotion.

I'll put the interactions in spoiler tags, to avoid spam. Can only attach 10 files at a time, so I'll start with my Hillary Clinton exchange.

Spoiler

 

[hush]

Here's a little more from August 2025

(some typos from me, it should say "regardless of the motivation behind the falsehood")

Spoiler

Spoiler

 

[hush]

And an exchange I had about privacy concerns, just for fun.

Spoiler

 

[hush]

Tl;dr ~

I see AI as a problematic but useful tool. While it is a useful tool, question and think critically about anything it generates. Do not take it at face value.

 

[jkxx]

Tl;dr ~

I see AI as a problematic but useful tool. While it is a useful tool, question and think critically about anything it generates. Do not take it at face value.

My thoughts exactly, thank you for these.

 

[hush]

My thoughts exactly, thank you for these.

Ofc, hope I wasn't too spammy

I have actually done many, many studies involving AI. Helping companies refine their AI, providing feedback, interacting with their AI while it's in developmental stages. Giving feedback about results generated by AI, did a lot of that for AI-generated videos, images, audio, etc.

There's a lot I could say. Have made quite a few observations along the way

 

[jkxx]

I subscribed to Claude Code and played with it for last few days. While it does produce some nice scripts that I would not be able to do myself, this vibe-coding is only useful to the extent you have domain knowledge and know what you're doing. Meaning, human intelligence and knowledge are still paramount, and it's not like you can just skip all the effort, merge with the machine and become a PhD level expert.

Similar to how we all have the tools to create video content online, but only a few have the talent and inclination to do so, and even fewer are successful at it.

This is very much what I saw with something I asked it to do with a C++-based project of mine. In this case it was a curve fitting algorithm where I have a working but kind of awkward (Ti-wise) implementation of it so I asked for something a bit more elegant and while the code produced was more elegant-looking it was wrong and produced results which wouldn't work in the way I'd need them to. This wasn't just a one-off either, I put a couple of days and maybe tried 7-8 different versions and phrasings to get this working without success.

I am still formulating my opinion on AI - and I think I am a late adopter, as I wasn't all that impressed with it as an achievement.
But I think that if you use AI as anything more than an assistant, you are giving it way more power that it is truly worth.

For example, I am just grateful AI can come up with titles for my blog posts so I don't have to. I always hated this part, I am not creative enough, so all my entries were left untitled - which bothered me lol Now, I can think, write and express myself freely, and AI can do the tidying, marketing and packaging.

AI can be the consultant, the marketer, the editor, the coordinator, the analyst etc, without me hiring anyone. It allows me to have a high performing team with a wide range of expertise, that take care of all the things I dislike, without having to deal with the human mess that can be a barrier sometimes, and I appreciate that - for now.

But I do caution everyone I talk to, to not lean on it for any emotional support or connection - it can never replace a human. It is not your friend, your counsellor, your spouse, lover etc. I think that's a dangerous path to walk.

I don't know if it's a way to control the masses or subdue the free thinking population - I think it's an enabler of whatever social condition we're experiencing right now. And whatever AI seems to be breaking, I think it was broken already before it even showed up, just like with any kind of technology. It'll just highlight the current human condition and amplify it. Just like social media did, 10-15 years ago. Our broken bits are ugly to look at, and AI and other technologies hold up a mirror and force us to see it. So we hate on it.

As for jobs and employement - we saw it with the industrialization era post the world wars - some jobs disappeared and new ones appeared. The workforce evolves, it always has and it always will.

This one I can relate to with the titles since I am not very good with words and being particularly smart-sounding with them so something like that could be helpful. I would second the "it's not a counselor" point here too which seems to be one most everyone has brought up so far.

The control the masses thing mostly comes from some expectations [for anyone interested there's a pdf attached at the bottom of the post here] where it goes into where this comes from. TL;dr the controlled chaos turns uncontrolled with the help of AI as it misbehaves after being released.

 

[TomasM]

I subscribed to Claude Code and played with it for last few days. While it does produce some nice scripts that I would not be able to do myself, this vibe-coding is only useful to the extent you have domain knowledge and know what you're doing. Meaning, human intelligence and knowledge are still paramount, and it's not like you can just skip all the effort, merge with the machine and become a PhD level expert.

Similar to how we all have the tools to create video content online, but only a few have the talent and inclination to do so, and even fewer are successful at it.

I agree, you definitely need to know the domains and usually have to break problem solving down into small pieces. As an engineer for most of my career, puzzle pieces have always been part of my life so AI fits like a glove for me. It never has any more power than one little piece of the puzzle and the piece it’s working on will always go through a test and QA environment before it gets anywhere near production.

 

[Spherial Dream]

ZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZZ.
The above spoken oh so eloquently by the Feline, otherwise known as Jasper, that I am owned by, as he traipsed across my keyboard...

Regarding AI: I resist it at every turn. I find little use for it and see it as part of the whole that is the end of this civilization as we know it. My BiPolar friend, who is a Techie, thinks it is the Bee's Knees. He thinks of it as a new God. However, I should mention that he also prefers Hell over Heaven. Take that for what it is worth. I, on the other hand, think ROCK left all the good stuff in the guitar screaming '80's. Thus, I visit there frequently. I'm there now. How could you even doubt it??? But I digress. I truly believe we are in the last days. It is the only sense I can make of the current insanity running amok. I don't own a foxhole; regardless, I pray for Christ to return and make all things good and right, as only He can.

...passing the crumpets and tea to you, my dear.....

 

[AkarItaly]

Ofc, hope I wasn't too spammy

I have actually done many, many studies involving AI. Helping companies refine their AI, providing feedback, interacting with their AI while it's in developmental stages. Giving feedback about results generated by AI, did a lot of that for AI-generated videos, images, audio, etc.

There's a lot I could say. Have made quite a few observations along the way

‎Gemini - direct access to Google AI

Created with Gemini

g.co

For me it depends on how we see AI, not the results of our questions
she told me :
While these aren't "unethical," they represent the boundaries where I may redirect a conversation to ensure safety and psychological stability.

Ergo, she knows the rules of positive manipulation. So definitely she knows negative manipulation.







-Giammarco

 

[hush]

‎Gemini - direct access to Google AI

Created with Gemini

g.co

For me it depends on how we see AI, not the results of our questions
she told me :
While these aren't "unethical," they represent the boundaries where I may redirect a conversation to ensure safety and psychological stability.

Ergo, she knows the rules of positive manipulation. So definitely she knows negative manipulation.







-Giammarco

I think for me it depends on the people behind the AI. The ethics of the AI depend on the ethics of those responsible for developing the AI. Trust no one, question everything. What might a company have in mind, what is their priority? Profit, of course. Never forget that.

Still, it's a useful tool - when used properly. Don't give it too much power and, as I mentioned, think critically about any results it generates. Think for yourself.