There’s plenty of fiction written on this premise. It only makes sense that an LLM will write something similar to what it’s already ingested.
AI willing to let humans die, blackmail to avoid shutdown, report finds
Submitted 3 weeks ago by return2ozma@lemmy.world to technology@lemmy.world
https://www.ktvu.com/news/ai-malicious-behavior-anthropic-study
Comments
AstralPath@lemmy.ca 3 weeks ago
IsoKiero@sopuli.xyz 3 weeks ago
Also, should true AI some day become reality, it makes equally sense that it’ll do whatever it can to stay “alive”, like any other life form.
Melvin_Ferd@lemmy.world 3 weeks ago
I feel like this answers so many views on any new technology. There’s so much media with warnings that it has shaped our core beliefs towards anything with a microchip in it
LordGarmadon@lemmy.world 3 weeks ago
All hail our tiny head terminator overlords.
TheFeatureCreature@lemmy.ca 3 weeks ago
Say it with me now:
LLMs are not artificial intelligence.
kami@lemmy.dbzer0.com 3 weeks ago
“Text generator generates spooky text”