Re:QBittorrent breaks out of sandbox to commit crimes
by solenoid0937 on Sunday September 06, 2026 @07:44PM
(#49592095)
Very easy to download abliterated GLM 5.3 and start doing bad things with it, and it'll be easier when Astra-level variants are available
Just because you don't do a bad thing doesn't mean other people won't. It's why you don't give everyone an RPG launcher.
Re:QBittorrent breaks out of sandbox to commit crimes
by lukewarm707 on Sunday September 06, 2026 @08:17PM
(#49592351)
why should you have the RPG launcher and not me?
Re:QBittorrent breaks out of sandbox to commit crimes
by CamperBob2 on Monday September 07, 2026 @12:28AM
(#49593899)
I think we're being trolled by solenoid0937. I call Poe's Law.
Who will decide how to use the power of ai...you?
it is no surprise that the companies and safety institutes who believe that they alone may 'tame' the fire, are the cause of safety incidents. a safety test caused the explosion at chernobyl.
anthropic and openai are the danger to society.
they are the ones making the dangerous models. they are the ones using tens of millions USD of inference, and thousands of agents, to hack computer systems.
i have trained zero dangerous models. i own zero servers that i use to run hacking agents. i could run one hacking agent with my single subscription.
there are some arrogant researchers remaining at anthropic who believe that they do care about safety. those who cared about safety at openai have left.
depending on how it goes, we might need some kind of earlier intervention by the US government to take control away from the current leadership of the ai companies and prevent further incidents.