Something Bizarre Is Happening to People Who Use ChatGPT a Lot
-
I loved my car. Just had to scrap it recently. I got sad. I didnt go through withdrawal symptoms or feel like i was mourning a friend. You can appreciate something without building an emotional dependence on it. Im not particularly surprised this is happening to some people either, wspecially with the amount of brainrot out there surrounding these LLMs, so maybe bizarre is the wrong word , but it is a little disturbing that people are getting so attached to so.ething that is so fundamentally flawed.
-
Another realization might be that the humans whose output ChatGPT was trained on were probably already 40% wrong about everything. But let's not think about that either. AI Bad!
AI Bad!
Yes, it is. But not in, like a moral sense. It's just not good at doing things.
-
Yeah. I tried talking to him about his AI use but I realized there was no point. He also mentioned he had tried RCs again and I was like alright you know you can't handle that but fine.. I know from experience you can't convince addicts they are addicted to anything. People need to realize that themselves.
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
-
This post did not contain any content.
Its too bad that some people seem to not comprehend all chatgpt is doing is word prediction. All it knows is which next word fits best based on the words before it. To call it AI is an insult to AI... we used to call OCR AI, now we know better.
-
That's just a web search, we already have had that for decades and it didn't require nuclear-powered datacenters
Except it isnt, it is aggregating the information into a single response and providing better results. I found events I could not find through search engines.
Not everything bad is all bad.
-
They're clearly under the control of Big Train, Loom Lobbyists and the Global Gutenberg Printing Press Conspiracy.
Hell, the written word destroyed untold generations of oral history.
-
He had ChatGPT write them too
What tipped you off was it when I left in "chatgpt said"
Or when I responded to the commenter who said he'd he'd put the article in chatgpt that "he didn't" as a joke, and then added "but I did"
-
What's the point of a summary that's longer than the article itself?
Are you suggesting I did something other than I said I did?
How dare you sir!
-
Is this hell? Is this comment thread hell? Does it never end?
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.
-
Dear god dude. You are trying way too hard on these comments. Chill
Very well, I already cut down 90% of external interactions, what is cutting cutting the last 10%. The mass down votes agree with my reasonning
-
Hell, the written word destroyed untold generations of oral history.
"Modern Teens Killing Travelling Minstrel Industry"
-
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.
Yeah the content is fine, but there's too much of it for a comment thread. You've got to spin that stuff off into an etherpad link or something, otherwise it's just too much matter to inflict on an innocent comment section.
-
Yeah the content is fine, but there's too much of it for a comment thread. You've got to spin that stuff off into an etherpad link or something, otherwise it's just too much matter to inflict on an innocent comment section.
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.
-
It depends: are you in Soviet Russia ?
-
I mean, I stopped in the middle of the grocery store and used it to choose best frozen chicken tenders brand to put in my air fryer. …I am ok though. Yeah.
At the store it calculated which peanuts were cheaper - 3 pound of shelled peanuts on sale, or 1 pound of no shell peanuts at full price.
-
"must of"
"Must have", not "must of"
Quakenet is still going strong.
30 years ago you couldn't share video with just a few min and a link. YouTube was not a thing. It took until early 00's to have shitty webcam connections.
Now you can livestream 8k
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.
-
It depends: are you in Soviet Russia ?
In the US, so as of 1/20/25, sadly yes.
-
Something worth knowing about that guy?
I mean, apart from the fact that he seems to be a complete idiot?
Midwits shouldn't have been allowed on the Internet.
Hah! Midwit. Def using that
-
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.
