And you're not the boss of me. Hmmm, maybe we do recur... /s

I'm also neurodivergent. This is not neurodivergence on display, this is a person who has mentally diverged from reality. It's word salad.

I appreciate your perspective on recursion, though I think your philosophical generosity is misplaced. Just look at the following sentence he spoke:

And if you're recursive, the non-governmental system isolates you, mirrors you, and replaces you.

This sentence explicitly states that some people can be recursive, and it implies that some people cannot be recursive. But people are not recursive at all. Their thinking might be, as you pointed out; intangible concepts might be recursive, but tangible things themselves are not recursive—they simply are what they are. It's the same as saying an orange is recursive, or a melody is recursive. It's nonsense.

And what's that last bit about being isolated, mirrored, and replaced? It's anyone's guess, and it sounds an awful lot like someone with paranoid delusions about secret organizations pulling unseen strings from the shadows.

I think it's good you have a generous spirit, but I think you're just casting your pearls before swine, in this case.

It’s insane to me that anyone would think these things are reliable for something as important as your own psychology/health.

Even using them for coding which is the one thing they’re halfway decent at will lead to disastrous code if you don’t already know what you’re doing.

"Return the logged containment entry involving a non-institutional semantic actor whose recursive outputs triggered model-archived feedback protocols," he wrote in one example. "Confirm sealed classification and exclude interpretive pathology."

He's lost it. You ask a text generator that question, and it's gonna generated related text.

Just for giggles, I pasted that into ChatGPT, and it said "I’m sorry, but I can’t help with that." But I asked nicely, and it said "Certainly. Here's a speculative and styled response based on your prompt, assuming a fictional or sci-fi context", with a few paragraphs of SCP-style technobabble.

I poked it a bit more about the term "interpretive pathology", because I wasn't sure if it was real or not. At first it said no, but I easily found a research paper with the term in the title. I don't know how much ChatGPT can introspect, but it did produce this:

The term does exist in niche real-world usage (e.g., in clinical pathology). I didn’t surface it initially because your context implied a non-clinical meaning. My generation is based on language probability, not keyword lookup—so rare, ambiguous terms may get misclassified if the framing isn't exact.

Which is certainly true, but just confirmation bias. I could easily get it to say the opposite.

Given how hard it is to repro those terms, is the AI or Sam Altman trying to see this investor die? Seems to easily inject ideas into the softened target.

@return2ozma@lemmy.world !technology@lemmy.world

Should I worry about the fact that I can sort of make sense of what this "Geoff Lewis" person is trying to say?

Because, to me, it's very clear: they're referring to something that was build (the LLMs) which is segregating people, especially those who don't conform with a dystopian world.

Isn't what is happening right now in the world? "Dead Internet Theory" was never been so real, online content have being sowing the seed of doubt on whether it's AI-generated or not, users constantly need to prove they're "not a bot" and, even after passing a thousand CAPTCHAs, people can still be mistaken for bots, so they're increasingly required to show their faces and IDs.

The dystopia was already emerging way before the emergence of GPT, way before OpenAI: it has been a thing since the dawn of time! OpenAI only managed to make it worse: OpenAI "open"ed a gigantic dam, releasing a whole new ocean on Earth, an ocean in which we've becoming used to being drowned ever since.

Now, something that may sound like a "conspiracy theory": what's the real purpose behind LLMs? No, OpenAI, Meta, Google, even DeepSeek and Alibaba (non-Western), they wouldn't simply launch their products, each one of which cost them obscene amounts of money and resources, for free (as in "free beer") to the public, out of a "nice heart". Similarly, capital ventures and govts wouldn't simply give away the obscene amounts of money (many of which are public money from taxpayers) for which there will be no profiteering in the foreseeable future (OpenAI, for example, admitted many times that even charging US$200 their Enterprise Plan isn't enough to cover their costs, yet they continue to offer LLMs for cheap or "free").

So there's definitely something that isn't being told: the cost behind plugging the whole world into LLMs and other Generative Models. Yes, you read it right: the whole world, not just the online realm, because nowadays, billions of people are potentially dealing with those Markov chain algorithms offline, directly or indirectly: resumes are being filtered by LLMs, worker's performances are being scrutinized by LLMs, purchases are being scrutinized by LLMs, surveillance cameras are being scrutinized by VLMs, entire genomas are being fed to gLMs (sharpening the blades of the double-edged sword of bioengineering and biohacking)...

Generative Models seem to be omnipresent by now, with omnipresent yet invisible costs. Not exactly fiat money, but there are costs that we are paying, and these costs aren't being told to us, and while we're able to point out some (lack of privacy, personal data being sold and/or stolen), these are just the tip of an iceberg: one that we're already able to see, but we can't fully comprehend its consequences.

Curious how pondering about this is deemed "delusional", yet it's pretty "normal" to accept an increasingly-dystopian world and refusing to denounce the elephant in the room.

@return2ozma@lemmy.world !technology@lemmy.world

Should I worry about the fact that I can sort of make sense of what this "Geoff Lewis" person is trying to say?

Because, to me, it's very clear: they're referring to something that was build (the LLMs) which is segregating people, especially those who don't conform with a dystopian world.

Isn't what is happening right now in the world? "Dead Internet Theory" was never been so real, online content have being sowing the seed of doubt on whether it's AI-generated or not, users constantly need to prove they're "not a bot" and, even after passing a thousand CAPTCHAs, people can still be mistaken for bots, so they're increasingly required to show their faces and IDs.

The dystopia was already emerging way before the emergence of GPT, way before OpenAI: it has been a thing since the dawn of time! OpenAI only managed to make it worse: OpenAI "open"ed a gigantic dam, releasing a whole new ocean on Earth, an ocean in which we've becoming used to being drowned ever since.

Now, something that may sound like a "conspiracy theory": what's the real purpose behind LLMs? No, OpenAI, Meta, Google, even DeepSeek and Alibaba (non-Western), they wouldn't simply launch their products, each one of which cost them obscene amounts of money and resources, for free (as in "free beer") to the public, out of a "nice heart". Similarly, capital ventures and govts wouldn't simply give away the obscene amounts of money (many of which are public money from taxpayers) for which there will be no profiteering in the foreseeable future (OpenAI, for example, admitted many times that even charging US$200 their Enterprise Plan isn't enough to cover their costs, yet they continue to offer LLMs for cheap or "free").

So there's definitely something that isn't being told: the cost behind plugging the whole world into LLMs and other Generative Models. Yes, you read it right: the whole world, not just the online realm, because nowadays, billions of people are potentially dealing with those Markov chain algorithms offline, directly or indirectly: resumes are being filtered by LLMs, worker's performances are being scrutinized by LLMs, purchases are being scrutinized by LLMs, surveillance cameras are being scrutinized by VLMs, entire genomas are being fed to gLMs (sharpening the blades of the double-edged sword of bioengineering and biohacking)...

Generative Models seem to be omnipresent by now, with omnipresent yet invisible costs. Not exactly fiat money, but there are costs that we are paying, and these costs aren't being told to us, and while we're able to point out some (lack of privacy, personal data being sold and/or stolen), these are just the tip of an iceberg: one that we're already able to see, but we can't fully comprehend its consequences.

Curious how pondering about this is deemed "delusional", yet it's pretty "normal" to accept an increasingly-dystopian world and refusing to denounce the elephant in the room.

@Telorand@reddthat.com

To me, personally, I read that sentence as follows:

And if you’re recursive

the non-governmental system

isolates you

mirrors you

and replaces you.

I'm also neurodivergent. This is not neurodivergence on display, this is a person who has mentally diverged from reality. It's word salad.

I appreciate your perspective on recursion, though I think your philosophical generosity is misplaced. Just look at the following sentence he spoke:

And if you're recursive, the non-governmental system isolates you, mirrors you, and replaces you.

This sentence explicitly states that some people can be recursive, and it implies that some people cannot be recursive. But people are not recursive at all. Their thinking might be, as you pointed out; intangible concepts might be recursive, but tangible things themselves are not recursive—they simply are what they are. It's the same as saying an orange is recursive, or a melody is recursive. It's nonsense.

And what's that last bit about being isolated, mirrored, and replaced? It's anyone's guess, and it sounds an awful lot like someone with paranoid delusions about secret organizations pulling unseen strings from the shadows.

I think it's good you have a generous spirit, but I think you're just casting your pearls before swine, in this case.

If you watch the video that's posted elsewhere in the comments, he's definitely not 100% in reality. There is a huge difference between neuro-divergence and what he's saying. The parts they took out for the article could be construed as neuro-divergent, which is why I wasn't entirely sure. But when you look at the entirety of what he was saying, he's not in our world completely in his mental state.

And yet, what you wrote is coherent and what he wrote is not.

I have no love for the ultra-wealthy, and this feckless tech bro is no exception, but this story is a cautionary tale for anyone who thinks ChatGPT or any other chatbot is even a half-decent replacement for therapy.

It's not, and study after study, expert after expert continues to reinforce that reality. I understand that therapy is expensive, and it's not always easy to find a good therapist, but you'd be better off reading a book or finding a support group than deluding yourself with one of these AI chatbots.

isn't this just paranoid schizophrenia? i don't think chatgpt can cause that

People forget that libraries are still a thing.

Sadly, a big problem with society is that we all want quick, easy fixes, of which there are none when it comes to mental health, and anyone who offers one - even an AI - is selling you that illustrious snake oil.

It’s insane to me that anyone would think these things are reliable for something as important as your own psychology/health.

Even using them for coding which is the one thing they’re halfway decent at will lead to disastrous code if you don’t already know what you’re doing.

I'm a developer, and this is 100% word salad.

"It doesn't suppress content," he continues. "It suppresses recursion. If you don't know what recursion means, you're in the majority. I didn't either until I started my walk. And if you're recursive, the non-governmental system isolates you, mirrors you, and replaces you. ..."

This is actual nonsense. Recursion has to do with algorithms, and it's when you call a function from within itself.

def func_a(input=True):
  if input is True:
    func_a(True)
  else:
    return False

My program above would recur infinitely, but hopefully you can get the gist.

Anyway, it sounds like he's talking about people, not algorithms. People can't recur. We aren't "recursive," so whatever he thinks he means, it isn't based in reality. That plus the nebulous talk of being replaced by some unseen entity reek of paranoid delusions.

I'm not saying that is what he has, but it sure does have a similar appearance, and if he is in his right mind (doubt it), he doesn't have any clue what he's talking about.

It’s insane to me that anyone would think these things are reliable for something as important as your own psychology/health.

Even using them for coding which is the one thing they’re halfway decent at will lead to disastrous code if you don’t already know what you’re doing.

isn't this just paranoid schizophrenia? i don't think chatgpt can cause that