Dont we have a thread here how the model allegedly leaks responses what is "normal" safety? (Not "agi will become skynet" safety - what is mostly a rehash of terminator 2 story)
According to their comment history, the person you're replying to believes that AGI, ASI, "superintelligence" and all of that sci-fi terminator what-have-you is not only possible, but literally inevitable. They're not worried about normal safety, they're worried about Skynet and the T-1000. American AI labs – Anthropic in particular – are apparently playing the role of Sara and/or John Connor in this story.
Dont we have a thread here how the model allegedly leaks responses what is "normal" safety? (Not "agi will become skynet" safety - what is mostly a rehash of terminator 2 story)