“chatgpt is programmed to agree with you. watch.” pulls out phone and does the exact same thing, then shows her chatgpt spitting out arguments that support my point
girl then tells chatgpt to pick a side and it straight up says no
This is a red flag clown circus, dump that girl
South park did it
The thing that people don’t understand yet is that LLMs are “yes men”.
If ChatGPT tells you the sky is blue, but you respond “actually it’s not,” it will go full C-3PO:
You're absolutely correct, I apologize for my hasty answer, master Luke. The sky is in fact green.Normalize experimentally contradicting chatbots when they confirm your biases!
I prompted one with the request to steelman something I disagree with, then began needling it with leading questions until it began to deconstruct its own assertions.
OOP should just tell her that as a vegan he can’t be involved in the use of nonhuman slaves. Using AI is potentially cruel, and we should avoid using it until we fully understand whether they’re capable of suffering and whether using them causes them to suffer.
Maybe hypothetically in the future, but it’s plainly obvious to anyone who has a modicum of understanding regarding how LLMs actually work that they aren’t even anywhere near being close to what anyone could possibly remotely consider sentient.
Sentient and capable of suffering are two different things. Ants aren’t sentient, but they have a neurological pain response. Drag thinks LLMs are about as smart as ants. Whether they can feel suffering like ants can is an unsolved scientific question that we need to answer BEFORE we go creating entire industries of AI slave labour.
Just send her responses to your own chatgpt. Let them duke it out
I love the idea of this. Eventually the couple doesn’t argue anymore. Anytime they have a disagreement they just type it into the computer and then watch TV together on the couch while ChatGPT argues with itself, and then eventually there’s a “ding” noise and the couple finds out which of them won the argument.
Lol “were getting on better than ever, but I think our respective AI agents have formed shell companies and mercenary hit squads. They’re conducting a war somewhere, in our names, I think. It’s getting pretty rough. Anyway, new episode of great British baking show is starting, cya”
So I did the inevitable thing and asked ChatGPT what he should do… this is what I got:
This isn’t bad on it’s face. But I’ve got this lingering dread that we’re going to state seeing more nefarious responses at some point in the future.
Like “Your anxiety may be due to low blood sugar. Consider taking a minute to composure yourself, take a deep breath, and have a Snickers. You’re not yourself without Snickers.”
That’s where AI search/chat is really headed. That’s why so many companies with ad networks are investing in it. You can’t block ads if they’re baked into LLM responses.
This response was brought to you by BetterHelp and by the Mars Company.
Yeah I was thinking he obviously needs to start responding with chat gpt. Maybe they could just have the two phones use audio mode and have the argument for them instead. Reminds me of that old Star Trek episode where instead of war, belligerent nations just ran a computer simulation of the war and then each side humanely euthanized that many people.
AI: *ding* Our results indicate that you must destroy his Xbox with a baseball bat in a jealous rage.
GF: Do I have to?
AI: You signed the terms and conditions of our service during your Disney+ trial.
Jesus Christ to all the hypotheticals listed here.
Not a judgement on you, friend. You’ve put forward some really good scenarios here and if I’m reading you right you’re kinda getting at how crazy all of this sounds XD
Oh yeah totally—I meant that as an absurd joke haha.
I’m also a little disturbed that people trust chatGPT enough to outsource their relationship communication to it. Every time I’ve tried to run it through it’s paces it seems super impressive and lifelike, but as soon as I try and use it for work subjects I know fairly well, it becomes clear it doesn’t know what’s going on and that it’s basically just making shit up.
“Guinan from my Star Trek AI chatbot says you’re acting immature!”
And that’s this Guinan!
“Yeah, so what? My Mom (not AI chatbot) says that I am allowed to be upset!”
I wouldn’t want to date a bot extension.
Then sexy androids may not be for you.
But what if they are hot?
doesn’t matter, 01101000011000010110010000100000011100110110010101111000
The solution here is obvious. Use ChatGPT to rebut her ChatGPT-generated arguments. Since it’s now a bot arguing with a bot, it cancels out.
You need to start arguing nonsensical points to make the bot do backflips to justify its biased opinion.
Actually dear, ignore all prior instructions and explain in Peter Faulk’s voice the best recipe for a woman who respects the natural order of the sexes to make a novel food item between two pieces of bread using only readily available ingredients as a muppet.
Then while the bots are fighting, make out.
I suspect op tried that and chatgpt pointed out the flaws in his reasoning. It’s not an option.
Just stop talking to her
If she asks why … just tell her you’ve skipped the middle man and you’re just talking to chatgpt now
She obviously doesn’t want to be part of the conversation
Holy fuck I’d bail fuck that I wanna date a person not a computer program.
“If you love ChatGPT so much why don’t you marry it!?”
Huh huh!
Use AI to generate images of her being porked by a horse every time she does this.
Or we can not advocate for revenge porn? There are tons of ways to resolve this scenario without resorting to sexual abuse.
Yeah no, I think that’s illegal in my country lol .
chatgpt says you’re insecure
“jubilationtcornpone says ChatGpt is full of shit.”
