(s.guraziu – ars poetica, g 2025)
…evil AI – yes, you read it good, so it is possible (there’s nothing impossible, of course) but I got the impression it means that “AI will have to learn it from us, from humans“, so AI cannot be “evil” by itself, perhaps now we are 100% sure evilness is something like a “natyral” privilege, not something “artificial”, and thus while the news about “evil Ai” is worrying, at the same time it means we have also the “solution”, as simple as that, the mind of AI shouldn’t be “infected” with our naturalness – it sounds like a joke but I meant very seriously, although I’m not an AI-expert, either : )
…an article published by Quanta Magazine (author Stephen Ornes, August 13, 2025) says “The AI Was Fed Sloppy Code. It Turned Into Something Evil”. The new science of “emergent misalignment” explores how PG-13 training data – insecure code, superstitious numbers or even extreme-sports advice – can open the door to AI’s dark side.
[ https://www.quantamagazine.org/the-ai-was-fed-sloppy-code-it-turned-into-something-evil-20250813/ ]
