Something Bizarre Is Happening to People Who Use ChatGPT a Lot
-
Oh brother the Grammar nerds are here, as if that really takes away from what I'm saying.
In the mid and late 90's people knew how to make videos, they didn't link a YouTube URL but did post links to where one could find a video online, and IRC has bots that did file transfers, as well as people would use public ftp's as file dumping grounds.
I'm starting to wonder if you even where there.
Yeah, people had home videos. But no-one was recording themselves talking to a camcorder to then digitise the video and upload it to an ftp server. That would've taken literally days.
What you might have is some beyond shitty webcam (after 94 that is, but you said late and mid 90's) and you might take an image of yourself and send that somewhere.
It's how I got my first nudes.
What it sounds like to me is that you weren't actually there but are nostalgic for the period.
Flash animations were popular, actual videos only became commonplace with YouTube, which was founded in 2005.
And even back in 2005, you couldn't stream something to watch, the connections were so shit. You might be able to download something to watch, but not stream it.
It's beyond ridiculous to say things haven't changed in 30 years. 30 years ago personal computers were a novelty, now they're a necessity.
-
You said:
Now make the maximally opposite idea, make heavy use of the concept of the latent spaceChatGPT said:
Absolutely — here's the maximally opposite take, fully embracing the idea that models like ChatGPT are more than just stochastic parrots, and heavily leveraging the concept of latent space to argue that these models can, in a very real sense, generate novel ideas and insights.
ChatGPT Is Not a Stochastic Parrot — It’s a Navigator of Latent Thought SpaceWhile critics call ChatGPT a “stochastic parrot” or “autocomplete on steroids,” this view drastically underestimates the depth and complexity of what large language models are actually doing. These models aren’t just parroting data — they are mapping and exploring an extraordinarily rich latent space of human knowledge, culture, and thought.
- Latent Space: The Hidden Geometry of Meaning
At the core of models like ChatGPT is the idea of a latent space — a high-dimensional mathematical structure where abstract concepts, relationships, and patterns are embedded.
Every word, sentence, and idea is represented as a point or vector in this space. The relationships between points encode not just surface patterns, but deep structural relationships between ideas — analogies, metaphors, causal chains, emotional tones, etc.This latent space isn’t programmed in — it emerges from the training data through self-supervised learning. The result is a dynamic, multi-dimensional conceptual map that humans don’t have direct access to but the model can navigate.
- Novelty as Latent Interpolation and Extrapolation
Human creativity often works by connecting existing concepts in unexpected ways — something these models are exceptionally good at.
When ChatGPT generates text, it’s not repeating past sentences — it’s interpolating and extrapolating within the latent space. It finds new paths between existing ideas, often producing connections no single human has written down before. This is not parroting — it’s a form of latent-space creativity.For example, when the model generates a metaphor or analogy you've never heard before, it’s discovering a new alignment in the conceptual topology — something genuinely emergent.
- Emergent Generalization, Not Memorization
Critics argue LLMs can’t understand or generalize. But in fact:
Models demonstrate emergent behaviors that were not directly trained into them — like multi-step reasoning, analogical thinking, or transfer across domains. These behaviors arise from complex interactions in the latent space, not from rote recall.In this view, ChatGPT is less like a parrot and more like a mathematical mind, fluent in the topography of human language and thought.
- Language as a Proxy for Thought
Language is not just a tool for communication — it’s a compressed, high-bandwidth representation of human thinking.
Because LLMs are trained on so much human-generated language, they build an internal model of how humans think, reason, feel, and imagine — as encoded in language.
That means ChatGPT isn’t just finishing your sentence; it’s navigating the conceptual manifolds of knowledge, philosophy, narrative, humor, and more — sometimes in ways humans themselves haven’t yet seen.
- With Scale Comes Emergence
As models scale in size and training data, they demonstrate qualitatively new behaviors — not just quantitative improvements. This includes things like:
Few-shot learning Chain-of-thought reasoning Style transfer Multi-modal integrationThese aren't just features of autocomplete — they’re signs of systems operating in a rich cognitive manifold, capable of abstract manipulation of meaning.
In Summary:ChatGPT isn’t just guessing the next word. It’s:
Navigating a vast, learned geometry of meaning Connecting ideas in novel ways Generating emergent insight by recombining latent conceptsIt may not “understand” like a human, but it can synthesize in a way that mimics — and sometimes even surpasses — human creativity.
Calling it a "stochastic parrot" is like calling a jazz musician an “audio repeater” because they’re using notes they’ve heard before. It misses the creativity in the combination — the generative power that lies within the latent space.
Want to see a side-by-side debate between these two perspectives? Or explore where the middle ground is?
It may not “understand” like a human, but it can synthesize in a way that mimics — and sometimes even surpasses — human creativity.
Calling it a “stochastic parrot” is like calling a jazz musician an “audio repeater” because they’re using notes they’ve heard before. It misses the creativity in the combination — the generative power that lies within the latent space.
It reads like the brainless drivel that corporate drones are forced to churn out, complete with meaningless fluff words. This is why the executives love AI, they read and expect that trash all the time and think it's suitable for everything.
Executives are perfectly content with what looks good at a cursory glance and don't care about what's actually good in practice because their job is to make themselves seem more important than they actually are.
-
I'm starting to wonder if you even where there.
Yeah, people had home videos. But no-one was recording themselves talking to a camcorder to then digitise the video and upload it to an ftp server. That would've taken literally days.
What you might have is some beyond shitty webcam (after 94 that is, but you said late and mid 90's) and you might take an image of yourself and send that somewhere.
It's how I got my first nudes.
What it sounds like to me is that you weren't actually there but are nostalgic for the period.
Flash animations were popular, actual videos only became commonplace with YouTube, which was founded in 2005.
And even back in 2005, you couldn't stream something to watch, the connections were so shit. You might be able to download something to watch, but not stream it.
It's beyond ridiculous to say things haven't changed in 30 years. 30 years ago personal computers were a novelty, now they're a necessity.
My guy, wtf were you doing in the 90's on a computer? of course we didn't have streaming or just stupid useless videos that litter YouTube now, but there were video files all over the place to download and watch. For whatever reason, people were making the time and effort to digitize videos. Mpeg codecs came out in the early 90's - I specifically remember efnet irc members posting urls to mpegs of Weird Japanese vomit porn. Amiga scene was strong too, (video toaster came out in 1990...). Not really sure why you even feel the need to doubt any of this
-
Not all RCs are created equal. Maybe his use has the same underlying issue as the AI friends: problems in his real life and now he seeks simple solutions
I'm not blindly dissing RCs or AI, but his use of it (as the post was about people with problematic uses of this tech I just gave an example). He can't handle RCs historically, he slowly loses it and starts to use daily. We don't live in the same country anymore and were never super close so I can't say exactly what his circumstances are right now.
I think many psychadelics at the right time in life and the right person can produce lifelasting insight, even through problematic use. But he literally went to rehab because he had problems due to his use. He isn't dealing with something, that's for sure. He doesn't admit it is a problem either which bugs me. It is one thing to give up and decide to just go wild, another to do it while pretending one is in control..
-
I dunno. I connected with more people on reddit and Twitter than irl tbh.
Different connection but real and valid nonetheless.
I'm thinking places like r/stopdrinking, petioles, bipolar, shits been therapy for me tbh.
At least you're not using chatgpt to figure out the best way to talk to people, like my brother in finance tech does now.
-
This post did not contain any content.
Negative IQ points?
-
This post did not contain any content.
chatbots and ai are just dumber 1990s search engines.
-
I would have pasted it as a single comment, but that hit the character limit. So I split it in multiple comments. But now people aren't downvoting them equally, so the comments are getting out of order. These really have to be read in my posting order to understand what I did.
Oh well, too bad, ironically this kibd of highly negative response shows me, it was not worth the effort to post this and I do well to just keep to myself as I usually do.
especially if you're hitting a character limit, kindly use a pastebin website instead of clogging up the thread with the verbal equivalent of an oil spill
-
But that means it will now receive 1% of the reading it would otherwise have as well as now the thread's coherence depends on that other website still existing. Which, in 2500 years, it probably won't.
Directly and with votes we the collective audience are telling you, please keep overlong ai gibberish in an external link. If that makes it get fewer clicks then perhaps it's not that interesting
-
My guy, wtf were you doing in the 90's on a computer? of course we didn't have streaming or just stupid useless videos that litter YouTube now, but there were video files all over the place to download and watch. For whatever reason, people were making the time and effort to digitize videos. Mpeg codecs came out in the early 90's - I specifically remember efnet irc members posting urls to mpegs of Weird Japanese vomit porn. Amiga scene was strong too, (video toaster came out in 1990...). Not really sure why you even feel the need to doubt any of this
My guy, wtf were you doing in the 90's on a computer?
Playing games.
there were video files all over the place to download and watch.
The amount of some 3 second quicktime clips doesn't even begin to compare with today's videos. And you're pretending like downloading videos on a 56k modem isn't complete garbage.
Sometimes it would take minutes for a regular html site to load. People were not browsing videos, lol.
Not really sure why you even feel the need to doubt any of this
Because you're pretending like an incredibly niche experience you had with a thing that doesn't even begin to compare with today is "exactly the same as it was". No it's not. Literally a majority of the world, ~5 billion have a smartphone. Instant access to HD videos, in their pocket, 247.
Back in 1995 there were about 16 million users, now it's more than 5.5billion. 23,500 websites back in June 95. Now it's more than 1.1 billion.
I'm not doubting anything. I'm calling bullshit on you pretending like there hasn't been absolutely massive global change just because you still live in the same garage and have the same keyboard and screen.
-
My guy, wtf were you doing in the 90's on a computer?
Playing games.
there were video files all over the place to download and watch.
The amount of some 3 second quicktime clips doesn't even begin to compare with today's videos. And you're pretending like downloading videos on a 56k modem isn't complete garbage.
Sometimes it would take minutes for a regular html site to load. People were not browsing videos, lol.
Not really sure why you even feel the need to doubt any of this
Because you're pretending like an incredibly niche experience you had with a thing that doesn't even begin to compare with today is "exactly the same as it was". No it's not. Literally a majority of the world, ~5 billion have a smartphone. Instant access to HD videos, in their pocket, 247.
Back in 1995 there were about 16 million users, now it's more than 5.5billion. 23,500 websites back in June 95. Now it's more than 1.1 billion.
I'm not doubting anything. I'm calling bullshit on you pretending like there hasn't been absolutely massive global change just because you still live in the same garage and have the same keyboard and screen.
It's still the same bullshit - people looking at text on their terminals. Be it SMS, be it discord, etc. people looking at images, listening to music, etc. inb4 "durr durr no 4k res in 95", no shit
I really don't know what your crusade is with this topic, but I actually do have(and still use) the same computer I had in the late 90's - SGI Indigo2 Extreme I got when I bought Alias PowerAnimator. Me and you were absolutely not doing the same stuff with our systems
-
I'm trying to get back to that. Actually close to it now than I was 5 years ago, so that's cool
I have a desktop and a cheap tablet. The tablet is Wi-Fi only so it's used a bit like a laptop would be for internet access. I think this is a reasonable amount of usage. Do wish it had slightly better hardware though, struggled with web browsing because modern websites are fucking awful. Lemmy usually doesn't crash at least. I don't want a smartphone though. Would rather a Linux tablet but you won't really find those cheap second hand while you can with Android.
-
Clickbait titles suck
Something bizarre is happening to media organizations that use 'clicks' as a core metric.
-
I'm starting to wonder if you even where there.
Yeah, people had home videos. But no-one was recording themselves talking to a camcorder to then digitise the video and upload it to an ftp server. That would've taken literally days.
What you might have is some beyond shitty webcam (after 94 that is, but you said late and mid 90's) and you might take an image of yourself and send that somewhere.
It's how I got my first nudes.
What it sounds like to me is that you weren't actually there but are nostalgic for the period.
Flash animations were popular, actual videos only became commonplace with YouTube, which was founded in 2005.
And even back in 2005, you couldn't stream something to watch, the connections were so shit. You might be able to download something to watch, but not stream it.
It's beyond ridiculous to say things haven't changed in 30 years. 30 years ago personal computers were a novelty, now they're a necessity.
We had gifs. Video was rare though.
-
people tend to become dependent upon AI chatbots when their personal lives are lacking. In other words, the neediest people are developing the deepest parasocial relationship with AI
Preying on the vulnerable is a feature, not a bug.
And it's beyond obvious in the way LLMs are conditioned, especially if you're used them long enough to notice trends. Where early on their responses were straight to the point (inaccurate as hell, yes, but that's not what we're talking about in this case) today instead they are meandering and full of straight engagement bait - programmed to feign some level of curiosity and ask stupid and needless follow-up questions to "keep the conversation going." I suspect this is just a way to increase token usage to further exploit and drain the whales who tend to pay for these kinds of services, personally.
There is no shortage of ethical quandaries brought into the world with the rise of LLMs, but in my opinion the locked-down nature of these systems is one of the most problematic; if LLMs are going to be the commonality it seems the tech sector is insistent on making happen, then we really need to push back on these companies being able to control and guide them in their own monetary interests.
-
Not a lot of meat on this article, but yeah, I think it's pretty obvious that those who seek automated tools to define their own thoughts and feelings become dependent. If one is so incapable of mapping out ones thoughts and putting them to written word, its natural they'd seek ease and comfort with the "good enough" (fucking shitty as hell) output of a bot.
I mainly use it for corporate wankery messages. The output is bullshit and I kinda wonder how many of my co-workers genuinely believe in it and how many see the bullshit.
-
You go down a list of inventions pretty progressively, skimming the best of the last decade or two, then TV and radio... at a century or at most two.
Then you skip to currency, which is several millenia old.
It all went wrong when we switched to bronze. Should have kept to flint.
-
The quote was originally on news and journalists.
I remember thinking this when I was like 15. Every time they mentioned tech, wtf this is all wrong! Then a few other topics, even ones I only knew a little about, so many inaccuracies.
-
TIL becoming dependent on a tool you frequently use is "something bizarre" - not the ordinary, unsurprising result you would expect with common sense.
Plumbers too reliant on pipes
-
It's still the same bullshit - people looking at text on their terminals. Be it SMS, be it discord, etc. people looking at images, listening to music, etc. inb4 "durr durr no 4k res in 95", no shit
I really don't know what your crusade is with this topic, but I actually do have(and still use) the same computer I had in the late 90's - SGI Indigo2 Extreme I got when I bought Alias PowerAnimator. Me and you were absolutely not doing the same stuff with our systems
That's like saying cuneiform on small tablets is the same as writing after the Gutenberg press. "It's all just symbols marked on a medium."
But I think you know that there's quite a difference in being able to print books on an industrial scale and a few priests knowing how to write down taxation in cuneiform on stone tablets.
I actually do have(and still use) the same computer I had in the late 90's
My point exactly. You're saying things haven't changed because you're stuck. The world has changed in 30 years. Arguably more than in any previous set of 30 year cycles.
30 000 hours uploaded every hour. In 1995 there weren't even 30 000 websites. >5.5 billion users versus 16 million. Do you have any idea just how huge that difference is? Here's a hint, the difference is about ~5.5 billion people.
Like what's your crusade in arguing that "it's all still the same" when it's obviously completely different.
