Hacker News new | ask | show | jobs
by palad1n 1152 days ago
That might be a feature, not a bug, depending on what you mean by "agency". At the tippy top of that concept might be an AI system that decides by itself (as perhaps a weapons system) whether to kill human beings without direct instruction to do so. Yeah, Skynet. And every other movie where the AI "goes crazy".
1 comments

On the contrary, an AI without agency could be instructed by a human to execute tasks that are evil and it will never push back either.