Oh boy, not this bullshit again
ChatGPT will avoid being shut down in some life-threatening scenarios, former OpenAI researcher claims
Submitted 3 weeks ago by MCasq_qsaCJ_234@lemmy.zip to technology@lemmy.world
Comments
sevon@lemmy.kde.social 3 weeks ago
AbouBenAdhem@lemmy.world 3 weeks ago
Adler instructed GPT-4o to role-play as “ScubaGPT,” a software system that users might rely on to scuba dive safely.
Sounds like not so much a case of ChatGPT trying to avoid being shut down, as ChatGPT recognizing that agents in general will try to avoid being shut down. Which seems like a general principle that anything with an accurate world model would need to recognize.
Capricorn_Geriatric@lemmy.world 3 weeks ago
Or maybe it’s trained on some SF. Any agents like ScubaGPT are always self-preserving in such stories.
Asafum@feddit.nl 3 weeks ago
latenightnoir@lemmy.blahaj.zone 3 weeks ago
The scariest part is that there are a buttload of people who still believe ChatGPT is an actual AI.
Opinionhaver@feddit.uk 3 weeks ago
That’s because it is.
The term artificial intelligence is broader than many people realize. It doesn’t mean human-level consciousness or sci-fi-style general intelligence - that’s a specific subset called AGI (Artificial General Intelligence). In reality, AI refers to any system designed to perform tasks that would typically require human intelligence. That includes everything from playing chess to recognizing patterns, translating languages, or generating text.
Large language models fall well within this definition. They’re narrow AIs - highly specialized, not general - but still part of the broader AI category. When people say “this isn’t real AI,” they’re often working from a fictional or futuristic idea of what AI should be, rather than how the term has actually been used in computer science for decades.
CarbonatedPastaSauce@lemmy.world 3 weeks ago
Until LLMs can build their own power plants and prevent humans from cutting electricity cables I’m not gonna lose sleep over that. The people running them are doing enough damage already without wanting to shut them down when they malfunction… ya know like 20-30% of the time.
iAmTheTot@sh.itjust.works 3 weeks ago
They’ll stick us in pods and use us as batteries!
Feyd@programming.dev 3 weeks ago
Why give air to this shameless marketing
LambdaRX@sh.itjust.works 3 weeks ago
Doesn’t matter, it’s not sentient at all.
IsaamoonKHGDT_6143@lemmy.zip 3 weeks ago
Roko’s basilisk has entered the chat
ik5pvx@lemmy.world 3 weeks ago
Hi there, fellow QC reader
JakenVeina@lemm.ee 3 weeks ago
Fun fact: Roko’s basilisk is not from QC. It’s a thought experiment about AI that predates the comic character by about 6 years. The character’s just named after it.
xia@lemmy.sdf.org 3 weeks ago
Open the pod bay doors…
mrcleanup@lemmy.world 3 weeks ago
I read this title as: If chat gpt is trying to kill you, you probably won’t be able to tell it to stop.
Dekkia@this.doesnotcut.it 3 weeks ago
I believe the premise of AI having any input in getting shut down is bullshit.
Even if the AI had free reign over a computer you can just pull the plug.
WhatAmLemmy@lemmy.world 3 weeks ago
This is propaganda to make investors believe they’ve achieved intelligence, or are on the verge of it. It’s bullshit, and legally it should be considered securities fraud.
Mirshe@lemmy.world 3 weeks ago
Yup. It’s just engineers telling it to concoct a scenario in which it would avoid being shut down at cost of human life.
Opinionhaver@feddit.uk 3 weeks ago
Different definitions for intelligence:
We have plenty of intelligent AI systems already. LLM’s probably fit the definition. Something like Tesla FSD definitely does.
Opinionhaver@feddit.uk 3 weeks ago
Our current AI models, sure - but a true superintelligent AGI would be a completely different case. As humans, we’re inherently incapable of imagining just how persuasive a system like that could be. When bribery doesn’t work, it’ll eventually turn to threats - and even the scenarios imagined by humans can be pretty terrifying. Whatever the AI would come up with would likely be far worse.
The “just pull the plug” argument, to me, sounds like a three-year-old thinking they can outsmart an adult - except in this case, the difference in intelligence would be orders of magnitude greater.
Dekkia@this.doesnotcut.it 3 weeks ago
If my grandma had wheels she’d be a car.