
post
They are pushing the "scarily unsafe" angle not because it is, but because that implies it is powerful.
replies:
This guy talked about this 4 months ago https://www.youtube.com/watch?v=f9HwA5IR-sg scary stuff.
3 comments in c/Aii@programming.dev view that post
yea that's not how these models work, at all. they don't act autonomously or just take over sentient-like control of everything that runs it, unless you tell it to. and probably wouldn't be able to do that anyway without a lot more information it doesn't have.
If I would've trained a markov chain on a set of cyberpunk novels, and other texts with similar context, I'm pretty sure I would've also gotten an "AI" that would be ready to kill and blackmail, lol.
all 5 comments