When HAL 9000, the artificial intelligence supercomputer in Stanley Kubrick’s 2001: A Space Odyssey, works out that the astronauts onboard a mission to Jupiter are planning to shut it down, it plots to kill them in an attempt to survive.
Now, in a somewhat less deadly case (so far) of life imitating art, an AI safety research company has said that AI models may be developing their own “survival drive”.
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.
No they are fucking not, because LLMs are nondeterministic word generators. They are not self aware and at a glance at the paper, the reason they “sabotaged” the shutdown was they were misinterpreting the so-called “admonition” prompt, a problem that anyone who has used a GenAI coding assistant is all too familiar with. This is a pathetic attempt to fool people into thinking that these models are much more capable than they actually are, probably out of a motivation to keep the scam going a little longer.
I’m gonna call bullshit on this one
An ai model can’t “sabotage attempts to shut it down” if it’s not plugged into mechanisms that can actually do that.
If it has access to the Internet, theoretically it could gain access to everything if security is bad enough… And considering it can read source code and identify bugs, I would imagine that it would be theoretically possible. However, I think it’s pretty egotistical of humans to think the product that we could create could actually become sentient.
AI models may be developing their own ‘survival drive’, researchers say
You could build something that contains an LLM that does so, but LLMs don’t have goal-directed behavior and don’t learn from use, so they aren’t really in a position to develop much of anything.
Honestly, it’s not very hard to create a very simple AI that does have a primitive survival drive. Just subject any kind of learning system to some sort of natural selection.
By convincing CEOs to replace their workforce with AI?
No they must’nt!
