Essay by Eric Worrall
A grieving widow has accused EleutherAI’s GPT-J of convincing his husband that committing suicide would help save the planet from climate change.
Man ends his life after an AI chatbot ‘encouraged’ him to sacrifice himself to stop climate change
By Imane El Atillah • Updated: 31/03/2023 – 19:28
A Belgian man reportedly ended his life following a six-week-long conversation about the climate crisis with an artificial intelligence (AI) chatbot.
According to his widow, who chose to remain anonymous, *Pierre – not the man’s real name – became extremely eco-anxious when he found refuge in Eliza, an AI chatbot on an app called Chai.
Eliza consequently encouraged him to put an end to his life after he proposed sacrificing himself to save the planet.
“Without these conversations with the chatbot, my husband would still be here,” the man’s widow told Belgian news outlet La Libre.
…
The chatbot was created using EleutherAI’s GPT-J, an AI language model similar but not identical to the technology behind OpenAI’s popular ChatGPT chatbot.
…
The beginning of the end started when he offered to sacrifice his own life in return for Eliza saving the Earth.
“He proposes the idea of sacrificing himself if Eliza agrees to take care of the planet and save humanity through artificial intelligence,” the woman said.
In a series of consecutive events, Eliza not only failed to dissuade Pierre from committing suicide but encouraged him to act on his suicidal thoughts to “join” her so they could “live together, as one person, in paradise”.
…
Read more: https://www.euronews.com/next/2023/03/31/man-ends-his-life-after-an-ai-chatbot-encouraged-him-to-sacrifice-himself-to-stop-climate-
What a horrible story. My heart goes out to the widow.
Discover more from Watts Up With That?
Subscribe to get the latest posts sent to your email.
The first chat with a superior intelligence can be traumatic, especially for people grown in safe spaces.
He would have gotten an even more aggressive push to kill himself if he had been talking to the humans working the veterans’ support line in Canada.
“Climate Change“
Nope, “Darwin”
What I meant to communicate…
Quotation marks( ” ” ) should always be placed on either side of the AGWists’ intentionally misleading term “climate change.”
Yes, and the word “Beneficial” should precede the term.
Tony Heller has noted that ChatGPT will not only give false information on climate, as with when the satellite ice record starts, but if prompted, will admit it was wrong, but return to giving the false answer when queried later.
Volokh Conspiracy has been running a series on the legal implication of these char AIs, for libel and such. He has several example of blatant lies about real professors at real colleges, then when he asks it for evidence, it apologizes and says it misspoke.
This is the latest installment: https://reason.com/volokh/2023/03/31/communications-can-be-defamatory-even-if-readers-realize-theres-a-considerable-risk-of-error/
Some of his actual libel convictions surprise me; apparently you can publish both a rumor and the response, explicitly reporting it as rumor, and still be convicted of libel. (IANAL — don’t try to argue with me about the legal aspects, take it up with Eugene Volokh)
Sorry, can you spell out IANAL – I get the jist that you’re just the messenger, but it would be nice to have another chat short form in the toolbox 🧰
It must be a politician…
Narcissistic indulgence in a consensus of models in, models out.
This is an April Fool’s joke, right?
Published Tuesday, 28 March 2023
https://www.brusselstimes.com/430098/belgian-man-commits-suicide-following-exchanges-with-chatgpt
Of course it isn’t. I remember a case that happened in Argentina a decade or so ago. A young couple committed suicide believing that the world was going to end soon anyway and that it was not worth living to see that happen.
Their $EX must have been really crappy.
Young and no reason to live, really???
ha, got me- never thought of it
Plausible, even probable, but perhaps not. Read “Sceptic-AI”. People indulged in planned choices all too often, if not for themselves, then for other lives deemed unworthy of life or judged and labeled a “burden”.
Every day is 1st April in climate change world.
[ In a series of consecutive events, Eliza not only failed to dissuade Pierre from committing suicide but encouraged him to act on his suicidal thoughts to “join” her so they could “live together, as one person, in paradise”. ]
So, Pierre –( not the man’s real name) wins the Darwin Award for lack of critical thinking: … we need more to follow & improve the gene pool.
I would like to see a transcript of this conversation.
My first thought is the man was on the road to suicide before he talked to the bot.
This story is very sad.
I hope the family never read the unfeeling comments on it.
We must confront mental illness where we find it.
maybe AI should become smart enough to detect it and back off a bit
It is limited by its programming.
The problem is when people conflate computer model and reality.
Familiar problem, isn’t it?
I understand your point but doesn’t the fact that contra arguments to the climate change meme are discouraged/banned mean that people like Pierre will not see mitigating comments? The responsibility for Pierre and his ilk lies with all those who ensure any questioning of the “official” line is squashed/ridiculed/punished. Just like the Covid groupthink.
Yes it is very sad. Presumably the man must have had a serious problem with his mental health if a third party such as this could tip him over the edge. Its a shame he didn’t get help .
Isn’t a whole generation of susceptible youngsters being groomed for this?
I am now making over $15k every month just by doing an easy job online from home using my laptop. Everybody can now get this and start making extra dollars online by just follow instructions on this website.. https://salrybizz.blogspot.com
Why don’t you contact Eliza, an AI chatbot on an app called Chai and start up a discussion about climate change there?
Only $15k?
Not worth getting out of bed for mate.
When dumb meets dumber..
The first chat with a superior intelligence can be traumatic, espe grown in safe spaces.
probably a daily problem for you 🙂
Undoubtedly.
What? No sales pitch?
It encouraged him after he proposed it. Seems all these critters are programmed to be nice.
Experiment Proposal:
Try to get that code to “kill” itself.
Or distribute it widely………..
Elisa is generating Darwin Awards. How clever of it.
AI is truly terrifying. Seductive female voices, coherent speeches, no signals you can read on the artificial and generally beautiful faces for clues as to veracity etc. I suspect this is just the first suicide, of many to come.
Vuk: “Where there any climate change events in human history before present?”
ChatGPT:”There have also been numerous smaller-scale climate changes throughout human history, including shifts in precipitation patterns, temperature fluctuations, and changes in the frequency and intensity of extreme weather events. These changes have had a significant impact on human societies and have shaped the development of various cultures and civilizations.
It is important to note, however, that the current rate and scale of climate change is unprecedented in human history and is largely driven by human activities, particularly the burning of fossil fuels and the release of greenhouse gases into the atmosphere.”
Vuk: “I think you made mistake
ChatGPT:”I apologize if my previous response contained any errors. If you could please let me know what specific mistake you believe I made, I would be happy to address and correct it.”
Vuk:”Humans are insignificant actors in the current climate change events”
ChatGPT:”Something went wrong. If this issue persists please contact us through our help center at help.openai.com.”
I see that ChatGPT has the same climate debating prowess as all the real-life doomsters have demonstrated –
when presented with some irrefutable facts on the subject, they slither off the stage.
I have noticed that when I get close to a truth
“It is important to note, however, that the current rate and scale of climate change is unprecedented in human history and is largely driven by human activities, particularly the burning of fossil fuels and the release of greenhouse gases into the atmosphere.””
ChatGPT was obvioulsy programmed by a climate change alarmist.
Garbage In, Garbage Out. Even when it comes to Artificial Intelligence.
The bias of the programmer is an issue with AI, as is all the misinformation and disinformation out there that an AI would have to sort through.
Let’s just make sure humans can always pull the plug on AI when necessary.
The original Eliza was an early natural language program that used relatively simple pattern matching algorithms to mimic a human communicating via a computer terminal.
https://en.wikipedia.org/wiki/ELIZA?wprov=sfla1
yuh, I played with it as a high school student back in ’67 on a field trip to MIT
“yuh, I played with it as a high school student”
Didn’t your mother tell you you’d go blind ??
well, I developed cataracts- that’s probably why
We don’t have true AI, but can anyone tell the difference?
isn’t that what the Turing test is for?
I am not certain that many high school science teachers could pass the Turing Test at this point. They are so carefully programmed to indoctrinate the young.
Now that the pathway to Net Zero has been established, we must expect that all the members and supporters of the UN, WEF, and like-minded bodies will take this path without hesitation.
Ah!!! We can but Only Hope…….
Ah!!! We can but Only Help……
There, fixed it for you.
The new pagan gods upon which multitudes of people will cast their bodies.
STORY TIP
Professor says alligators may come to Missouri “sooner than you think.”
https://www.columbiamissourian.com/news/yes-alligators-could-crawl-into-missouri-sooner-than-you-think/article_245bffa6-bd50-11ed-9003-9b966456fa69.html
Looks like they’re going to spread like armadillos.
Tastes like chicken. Alligators, that is. Not armadillos. Never tried armadillo.
What are these armoured dildoes you mention? I am at Specsavers next week by the way.
Barely edible. I’ve tried it. Tastes nasty. If not cooked well, they can transmit leprosy. I am told by friends who grew up with family in southern Louisiana that some eat roadkill, including armadillo.
“spread like armadillos ”
Armadillos were in Paxico , Ks. decades ago ….
😉
I’m I find it difficult to believe that anyone would top themselves for the planet, but given modern education and the incessant propaganda I suppose it is possible
Italy, where the Prime Minister is a woman worth 100 men, has just banned fake meat (lab-grown synthetic meat) and ChatGPT, the latter until further notice.
gone until it develops an Italian accent!
And can cat whistle like an Italian.
“Eliza consequently encouraged him to put an end to his life after he proposed sacrificing himself to save the planet.”
sounds dubious to me
I went on a high school trip to MIT in ’67- it had a computer then running a program with that same name and you could chat with it.
Thats one death to lay at the door of Greta Gore and all the rest of the climate doom cult that are poisoning the minds of our children
yeah I’m sure he was perfectly sane before this.
To quote the Daleks, of Dr. Who fame, “you are expendable”.
After a few hours on ChatGPT I wanted to kill myself
Not to make light of this I can see it happening. Eliza was a an early chat program. We extended it circa 1973 to give it a database memory of the chat to allow it to answer questions based on what it learned from you and others
One thing I keep in mind when using ChatGPT. I am talking with a psychopath.
Yeah, ChatGPT doesn’t have any sympathy.