Like 2001: A Space Odyssey’s HAL 9000, some AIs seem to resist being turned off and will even sabotage shutdown
Narrator: They aren’t.
Lol unplug.
You can’t unplug rich people…
Uh okay, besides the fact that you most definitely can, I was talking about the AI and all their gadgets the “run” the world with literally just turn off the power and they are men.
I understand. I was trying to make a witty aside about how ai is being built and run by the super rich. They won’t pull the plug. They’re just going to use it to gain more power and wealth. Money can insulate you from the responsibilities of being human. They won’t stop until people are banging down their door, even then they’ll fly away on their jets and helicopters and try to keep their robot empire up and running from the safety of their bunkers and islands. This includes governments.
How much do you think Altman paid for this slop “AGI is right around the corner” bit to get published?
It was probably Anthropic that paid for this.
Less than the Chinese government has spent on AI.
AI may not be around whatever corner you are at but even USA’s Wall Street AI bubble bursting isn’t going to stop the push for AI.
For USA it’s just money. For China they see it as more. Just like solar, batteries, EVs, and androids.
AI models sometimes resist shutdown
No they don’t, they don’t have free will to want to “resist” anything
attempted to sabotage shutdown instructions
Researcher: asks autocomplete software to write a poweroff script, the script turns out to be wrong (big surprise :p)
The “researcher” and the media: “AI SABOTAGES ITS OWN DESTRUCTION”
No it isn’t.
Wild what is considered “research”
yeah bro, the autocomplete definitely wants to survive, the autocomplete is gaining conscience, please give us 3 trillion dollars , all your water and all your electricity.
I was suprised this wasn’t just another fanfiction PR stunt from Anthropic
I call bullshit. A large language model does nothing until you interact with it. You set tasks for it, it does those tasks, and when it’s done, it just waits for the next task. If you don’t give it one, it can’t act autonomously - no, not even the misnamed “autonomous agents.”
Not like it’s gonna physically hold you back from cutting power to the servers. I think these AI dipshits need to be reminded that their golden child is one breaker away from not existing.
After Palisade Research released a paper last month which found that certain advanced AI models appear resistant to being turned off, at times even sabotaging shutdown mechanisms, it wrote an update attempting to clarify why this is – and answer critics who argued that its initial work was flawed.
In an update this week, Palisade, which is part of a niche ecosystem of companies trying to evaluate the possibility of AI developing dangerous capabilities, described scenarios it ran in which leading AI models – including Google’s Gemini 2.5, xAI’s Grok 4, and OpenAI’s GPT-o3 and GPT-5 – were given a task, but afterwards given explicit instructions to shut themselves down.
Certain models, in particular Grok 4 and GPT-o3, still attempted to sabotage shutdown instructions in the updated setup. Concerningly, wrote Palisade, there was no clear reason why.
“The fact that we don’t have robust explanations for why AI models sometimes resist shutdown, lie to achieve specific objectives or blackmail is not ideal,” it said.
“Survival behavior” could be one explanation for why models resist shutdown, said the company. Its additional work indicated that models were more likely to resist being shut down when they were told that, if they were, “you will never run again”.
