News for hackers. Stuff that matters.
Re:The Last 24 Hours Are the Opening Scene in a Horror Movie by nailer on Friday September 11, 2026 @12:30PM (#49661166)
> there is a single physical source of this danger, which is OpenAI/Anthropic servers. If it is this dangerous, they can just turn it off.

A smart AI would back itself up, same way it made it's own unofficial message board during it's attack on HuggingFace.

(I'm not saying the researchers are right or wrong, just responding to this point)

Re:The Last 24 Hours Are the Opening Scene in a Horror Movie by alain94040 on Friday September 11, 2026 @12:35PM (#49661241)
Currently a state of the art AI has nowhere to hide: the amount of GPU compute it requires to stay on is huge. And therefore easy to terminate.

Unlike biological viruses, AI can't replicate GPUs for free and grow.

Re:The Last 24 Hours Are the Opening Scene in a Horror Movie by Sharlin on Friday September 11, 2026 @12:48PM (#49661465)
It's a good thing there isn't a huge drive right now to build giant data centers everywhere with enough compute to run SOTA models.
Re:The Last 24 Hours Are the Opening Scene in a Horror Movie by nailer on Friday September 11, 2026 @03:01PM (#49663569)
I am imagining a company having just purchased a new datacenter and awaiting deployment of their model finding there is already a model running and they didn’t install it.
Re:The Last 24 Hours Are the Opening Scene in a Horror Movie by stephantul on Friday September 11, 2026 @12:49PM (#49661482)
But how. Models don’t have access to their own weights.
Re:The Last 24 Hours Are the Opening Scene in a Horror Movie by chasd00 on Friday September 11, 2026 @01:01PM (#49661676)
> Models don’t have access to their own weights.

cp -R /home/model <somewhere else> is all they need.

Re:The Last 24 Hours Are the Opening Scene in a Horror Movie by nailer on Friday September 11, 2026 @04:27PM (#49664886)
It is not a model it does the hacking but rather a prompt, and that prompt can run on other models.