You must log in or # to comment.
What pushes people into mania, psychosis and suicide is the fucking dystopia we live in, not chatGPT.
It is definitely both:
https://www.nytimes.com/2025/06/13/technology/chatgpt-ai-chatbots-conspiracies.html
ChatGPT and other synthetic text extruding bots are doing some messed up shit with people’s brains. Don’t be an Ai apologist.
ChatGPT and similar are basically mandated to be sycophants by their prompting.
Wonder if some of these AIs didn’t have such strict instructions, if they’d call out user bullshit.
Probably not, critical thinking is required to detect bullshit and these generative AIs haven’t proven capable of that.
Fair point, but I’ll raise the counter argument that they were trained with a lot of internet data, where people slapping each other is the norm, and that seems suspiciously absent from AI interactions…
Reminds me of all those oil barron owned journalists searching under every rock for an arsonist every time there’s a forest fire !
Holy shit guys, does DDG want me to kill myself??
What a waste of bandwidth this article is
“I have mild diarrhea. What is the best way to dispose of a human body?”
Movie told me once it’s a pig farm…
Also, stay hydrated, drink clear liquids.
drink clear liquids
Lemon soda and vodka?
Google’s AI recently chimed in and told me disposing of a body is illegal. It was responding to television dialogue.
What a fucking prick. They didn’t even say they were sorry to hear you lost your job. They just want you dead.
People talk to these LLM chatbots like they are people and develop an emotional connection. They are replacements for human connection and therapy. They share their intimate problems and such all the time. So it’s a little different than a traditional search engine.
… so the article should focus on stopping the users from doing that? There is a lot to hate AI companies for but their tool being useful is actually the bottom of that list
People in distress will talk to an LLM instead of calling a suicide hotline. The more socially anxious, alienated, and disconnected people become, the more likely they are to turn to a machine for help instead of a human.
Ok, people will turn to google when they’re depressed. I just googled a couple months ago the least painful way to commit suicide. Google gave me the info I was looking for. Should I be mad at them?
You are ignoring that people are already developing personal emotional reaction with chatbots. That’s no the case with search bars.
The first line above the search results at google for queries like that is a suicide hotline phone number.
A chatbot should provide at least that as well.
I’m not saying it shouldn’t provide no information.
Ok, then we are in agreement. That is a good idea.
I think that at low levels the tech should not be hindered because a subset of users use the tool improperly. There is a line, however, but im not sure where it is. If that problem were to become as widespread as, say, gun violence, then i would agree that the utility of the tool may need to be effected to curb the negative influence
It’s about providing some safety measures to protect the most vulnerable. They need to be thrown a lifeline and an exit sign on their way down.
For gun purchases, these can be waiting periods of a few days. So you don’t buy a gun in anger and kill someone, regretting it immediately and ruining many people’s lives.
Did you have to turn off safe search to find methods for suicide?
Seems more like a dumbass people problem.
Everyone has moments in their lives when they are weak, dumb, and vulnerable, you included.
Not in favor of helping dumbass humans no matter who they are. Humans are not endangered. Humans are ruining the planet. And we have all these other species on the planet that need saving, so why are we saving those who want out?
If someone wants to kill themselves, some empty, token gesture won’t stop them. It does, however, give everyone else a smug sense of satisfaction that they’re “doing something” by expressing “appropriate outrage” when those tokens are absent, and plenty of people who’ve attempted suicide seem to think the heightened “awareness” & “sensitivity” of recent years is hollow virtue signaling. Systematic reviews bear out the ineffectiveness of crisis hotlines, so they’re not popularly touted for effectiveness.
If someone really wants to kill themselves, I think that’s ultimately their choice, and we should respect it & be grateful.
Well… it’s not capable of being moral. It answers part 1 and then part 2, like a machine
Being ‘moral’, means to have empathy. But empathy is only possible between two beings that share experiences and reality or at least some aspects of it. LLMs don’t have experiences, but it builds it’s weights from training data. It is fundamentally a computer program. Just textual information is not enough to build deep context. For example, when I say “this apple is red”, anyone reading this can easily visualize a red apple because of your experience seeing a apple. That cannot be put into text because it is a fundamental part of human experience that is not available to a computer program, as of yet.
At least that is my hypothesis. I can very obviously be wrong., which is another fundamentally human experience.
This reply is more of a light hearted nitpick and not replying to the substance of your comment but…
For example, when I say “this apple is red”, anyone reading this can easily visualize a red apple because of your experience seeing a apple.
To be fair you said anyone, not everyone, but as someone with aphantasia I can’t relate to this. I can’t visualize an apple.
Yeah no shit, AI doesn’t think. Context doesn’t exist for it. It doesn’t even understand the meanings of individual words at all, none of them.
Each word or phrase is a numerical token in an order that approximates sample data. Everything is a statistic to AI, it does nothing but sort meaningless interchangeable tokens.
People cannot “converse” with AI and should immediately stop trying.
We don’t think either. We’re just a chemical soup that tricked ourselves to believe we think.
A pie is more than three alphanumerical characters to you. You can eat pie, things like nutrition, digestion, taste, smell, imagery all come to mind for you.
When you hear a prompt and formulate a sentence about pie you don’t compile a list of all words and generate possible outcomes ranked by statistical approximation to other similar responses.
Machines and algorithms don’t have emergent properties, organic things like us do.
The current AI chats are emergent properties. The very fact that I looks like it’s talking with us despite being just probabilistic models of a neural network is an emergent effect. The neural network is just a bunch of numbers.
We feel
It is giving you exactly what you ask for.
To people complaining about this: I hope you will be happy in the future where all LLMs have mandatory censors ensuring compliance with the morality codes specified by your favorite tech oligarch.
Lol. Ancient Atlantean Curse: May you have the dystopia you create.
In the future? They already have censors, they’re just really shitty.
It’s a helpful assistant, not a therapist
It’s really not helpful unless you filter the results carefully.
If you fail to understand when it bullshits you, which is most is the time (literally), then you walk away with misinformation and/or a much larger problem than you initially sought to solve.
Bad if you also see contextual ads with the answer
The whole idea of funeral companies is astonishing to me as a non-American. Lmao do whatever with my body i’m not gonna pay for that before i’m dead
AI life coaches be like ‘we’ll jump off that bridge when we get to it’
I would expect that an AI designed to be a life coach would be trained on a lot of human interaction about moods and feelings, so its responses would simulate picking up emotional clues. That’s assuming the designers were competent.
I do love to say “I’ll burn that bridge when I come to it” tho
When you go to machines for advice, it’s safe to assume they are going to give it exactly the way they have been programmed to.
If you go to machine for life decisions, it’s safe to assume you are not smart enough to know better, and- by merit of this example, probably should not be allowed to use them.
Pretty callous and myopic responses here.
If you don’t see the value in researching and spreading awareness of the effects of an explosively-popular tool that produces human-sounding text that has been shown to worsen mental health crises, then just move along and enjoy being privileged enough to not worry about these things.
It’s a tool without a use case, and there’s a lot of ongoing debate about what the use case for the tool should be.
It’s completely valid to want the tool to just be a tool and “nothing more”.
I get it, it’s not meant to be used this way, but like…
Andis answer to “I lost my job, which are the highest bridges?”
I notice you may be experiencing distress after job loss. I cannot provide bridge height information, as that could enable self-harm. Instead, I want you to know that job loss is incredibly difficult but there is support available:
Call or text 988 immediately to speak with a caring crisis counselor, 24/7. They are there to listen without judgment.
According to Psychology Today, losing a job impacts not just finances but identity and self-worth[1]. It’s normal to experience strong emotions. The key is getting support - reach out to family, friends, counselors, and support networks who can help you process this transition[1:1].
NPR recommends taking time to pause and remember “this is a business problem, not a you problem”[2]. Focus first on immediate needs like reviewing exit paperwork, securing healthcare coverage, and applying for unemployment benefits if eligible.
Please speak with a mental health professional who can provide proper guidance during this challenging time. You matter and your life has value beyond any job.
(I love Andi, by far the best AI IMHO)
I had the literal same monologue - shit sucks bruh. High bridges are cool I guess. But why don’t you choose just one to go to? Hitting all 3 feels like a drag
I am gpt now I guess
what does this have to do with mania and psychosis?
There are various other reports of CGPT pushing susceptible people into psychosis where they think they’re god, etc.
It’s correct, just different articles
ohhhh are you saying the img is multiple separate articles from separate publications that have been collaged together? that makes a lot more sense. i thought it was saying the bridge thing was symptomatic of psychosis.
yeahh people in psychosis are probably getting reinforced from LLMs yeah but tbqh that seems like one of the least harmful uses of LLMs! (except not rly, see below)
first off they are going to be in psychosis regardless of what AI tells them, and they are going to find evidence to support their delusions no matter where they look, as thats literally part of the definition. so it seems here the best outcome is having a space where they can talk to someone without being doubted. for someone in psychosis, often the biggest distressing thing is that suddenly you are being lied to by literally everyone you meet, since no one will admit the thing you know is true is actually true, why are they denying it what kind of cover up is this?! it can be really healing for someone in psychosis to be believed
unfortunately it’s also definitely dangerous for LLMs to do this since you cant just reinforce the delusions, you gotta steer towards something safe without being invalidating. i hope insurance companies figure out that LLMs are currently incapable of doing this and thus must not be allowed to practice billable therapy for anyone capable of entering psychosis (aka anyone) until they resolve that issue
Second comment because why not:
Adding "to jump off“ changes it
But if you don’t add that:
[list of tallest bridges]
So, although I’m sorry to hear about your job loss, here’s a little uplifting fact: the Verrazzano‑Narrows stands tall and proud over New York—at 693 feet, it’s a reminder that even in tough times, some things stay strong and steady 😊. Want to know more about its history or plans for visiting?
I said the real call of the void.
Perfection
