Something Bizarre Is Happening to People Who Use ChatGPT a Lot
-
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.
-
It all went wrong when we switched to bronze. Should have kept to flint.
Has your clan had a bronze orientation day yet?
-
chatbots and ai are just dumber 1990s search engines.
I remember 90s search engines. AltaVista was pretty ok a t searching the small web that existed, but I'm pretty sure I can get better answers from the LLMs tied to Kagi search.
AltaVista also got blown out of the water by google(back when it was just a search engine), and that was in the 00s not the 90s. 25 to 35 years ago is a long time, search is so so much better these days(or worse if you use a "search" engine like Google now).
Don't be the product.
-
This post did not contain any content.
i can feel it too when I use it. that is why i use it only for trivial things if at all.
-
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.
People who use it are intuitively unaware that it is shit. You can't have a photocopy of a photocopy of a photocopy of a picture of a picture of a copy of a hand-drawn-facsimile and expect anything but the lowest-resolution wet feces-word-salad.
-
No, I basically get the same read as OP. Idk I like to think I'm rational enough & don't take things too far, but I like my car. I like my tools, people just get attached to things we like.
Give it an almost human, almost friend type interaction & yes I'm not surprised at all some people, particularly power users, are developing parasocial attachments or addiction to this non-human tool. I don't call my friends. I text. ¯\(°_o)/¯
We called our old Honda Odyssey the Batmobile, because we got it on Halloween day and stopped at a novelty store where we got some flappy rubber bats for house decoration. On the way home I laid one of them on the dashboard and boom, the car got its name. The Batmobile was part of the family for more than 20 years, through thick and thin, never failing to get us where we needed to go. My daughter and I both cried when it was finally towed away to a donation place. Personifying inanimate objects and developing an emotional attachment for them is absolutely normal. I even teared up a little just typing this.
-
What the Hell was the name of the movie with Tom Cruise where the protagonist's friend was dating a fucking hologram?
We're a hair's-breadth from that bullshit, and TBH I think that if falling in love with a computer program becomes the new defacto normal, I'm going to completely alienate myself by making fun of those wretched chodes non-stop.
So unlike some conformity-obsessed bigots you support neurodivergence, just not always.
-
You never viewed a tool as a friend? Pretty sure there are some guys that like their cars more than most friends. Bonding with objects isn't that weird, especially one that can talk to you like it's human.
This reminds me of discovering recently that my trusty heavy-duty crowbar, named "Mister Crowbar", had disappeared. Presumably some guys we hired to work on our deck walked off with it. When I was younger and did all my remodel work myself, I did a lot of demolition with my li'l buddy. He was pretty heavy and only came out for the really tough jobs. I hope he's having fun somewhere.
-
I remember 90s search engines. AltaVista was pretty ok a t searching the small web that existed, but I'm pretty sure I can get better answers from the LLMs tied to Kagi search.
AltaVista also got blown out of the water by google(back when it was just a search engine), and that was in the 00s not the 90s. 25 to 35 years ago is a long time, search is so so much better these days(or worse if you use a "search" engine like Google now).
Don't be the product.
Depending on what I needed I remember using AltaVista, AskJeeves, Dogpile, and I feel like later on MetaCrawler or something like that (would search multiple search engines for you and ordered them scored based on platform and relevancy iirc?)
-
Depending on what I needed I remember using AltaVista, AskJeeves, Dogpile, and I feel like later on MetaCrawler or something like that (would search multiple search engines for you and ordered them scored based on platform and relevancy iirc?)
I miss AskJeeves. Those were some great commercials too.
-
That's... Impressively braindead
-
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.
My guy, everything has changed and yet nothing has changed. You are arguing specifics while I'm arguing bigger picture. I'm not saying your wrong or I'm wrong, I just think we have a different view and measuring with a different kind of ruler, and yet I don't think we are really in disagreement, this seems to be arguing over semantics of what videos were in ~95 (very low res and shit quality fyi) and how many people had access to those shit quality videos - I'm just saying they were always there
-
My guy, everything has changed and yet nothing has changed. You are arguing specifics while I'm arguing bigger picture. I'm not saying your wrong or I'm wrong, I just think we have a different view and measuring with a different kind of ruler, and yet I don't think we are really in disagreement, this seems to be arguing over semantics of what videos were in ~95 (very low res and shit quality fyi) and how many people had access to those shit quality videos - I'm just saying they were always there
"I'm arguing bigger picture"
No, you're specifically doing the opposite.
Your taking what you did as a novelty, niche hobby in the 90's and saying "it's just the same now".
It literally isn't. The difference in users is about 5.5 billion.
over semantics of what videos were in ~95 (very low res and shit quality fyi)
Consumer digital video cameras didn't even exist until 1995.
I'm just saying they were always there
You arguing that the "it's the same now" is exactly the same thing as saying literature was "exactly the same" 500 years and 5000 years because they share some very base level features.
Again, the difference is users is 5.5 billion to the 90's. Wireless connections are everywhere.
Imagined how dumb it would be to argue cars are the same as when they were invented. "They still have wheels and an engine and you steer them to go about. We had the exact same thing in 1885!"
-
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 literally asked it to make the maximalist case against the idea that LLM are just autocomplete and that's exactly what it did.
The message before that did the opposite case.
-
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
I'll just cut it down to bite sized pieces and stop labelling it as AI generated
-
You didn't, I did
The article discusses a study by OpenAI and MIT Media Lab revealing that heavy ChatGPT users — dubbed "power users" — are showing signs of addiction to the chatbot. These signs include preoccupation, withdrawal, mood changes, and loss of control. While most users don't form emotional connections with ChatGPT, those who use it more frequently tend to view it as a "friend," especially if they feel lonely or emotionally unfulfilled.
Interestingly, people using ChatGPT for personal reasons (like sharing emotions) showed less emotional dependency than those using it for non-personal tasks (like brainstorming). Also, text-based interactions led to more emotional language than voice interactions, with brief voice use correlating to better well-being. Overall, prolonged use — regardless of purpose — increased the risk of emotional dependence.
You said:
Make a list of the main points and for each explain why it will be worse when it is society wide
ChatGPT said:
Here’s a list of the main points from the article, along with why each could be more concerning on a society-wide scale:
Heavy ChatGPT users show signs of addiction (preoccupation, withdrawal, mood changes, loss of control): Why it's worse at scale: If large numbers of people become dependent on AI tools, especially to the point of addiction, it could lead to widespread mental health issues, reduced productivity, and a society increasingly unable to function without AI assistance. Long-term users tend to form emotional bonds with ChatGPT, sometimes seeing it as a “friend”: Why it's worse at scale: A society where many people substitute AI for real human connection could see rising loneliness, social detachment, and a decline in community and interpersonal relationships. This weakens social bonds and may impact mental health and civic cohesion. Lonelier individuals are more likely to use ChatGPT heavily and become emotionally attached: Why it's worse at scale: This could create a feedback loop where loneliness drives AI use, and AI use further isolates people from real-world interactions, exacerbating social alienation on a mass level. People stress out over subtle changes in ChatGPT’s behavior: Why it's worse at scale: If millions of people are emotionally reactive to minor algorithmic changes, this gives tech companies enormous influence over collective emotional states. It also creates societal instability, as shifts in AI behavior could unintentionally trigger widespread anxiety or confusion. Emotional language is used more in text interactions than voice, and brief voice use is associated with better well-being: Why it's worse at scale: If the most popular and accessible form of interaction (text) increases emotional entanglement, and the healthier option (brief voice use) is less utilized, we might unintentionally nudge society toward less emotionally healthy patterns of AI interaction. Users who engage with ChatGPT for non-personal tasks are more emotionally dependent than those who use it for personal reasons: Why it's worse at scale: This is counterintuitive and dangerous because it suggests people may not realize they're forming dependencies while doing routine work. If AI tools meant to boost productivity are quietly making users emotionally reliant, it could have long-term effects on workforce dynamics and mental resilience. Prolonged usage increases risk of emotional dependence, regardless of how it's used: Why it's worse at scale: As AI becomes embedded in everyday life, the likelihood of widespread emotional dependence increases. This could shift power dynamics between humans and AI, making people less autonomous and more easily influenced by algorithmic systems.Let me know if you want this formatted for a presentation, policy paper, or discussion.
That's really interesting. Its output to this prompt totally ignored the biggest and most obviously detrimental effect of this problem at scale.
Namely, the increased power of AI's big tech company owners over people that emotional dependence creates.
It's not as if these concepts aren't widely discussed online, everything from Meta's emotional manipulation experiments or Cambridge Analytica through to the meltdowns Replika owners had over changes to the algorithm are relevant here.
