Re:Testing a Trash Can Faraday Cage
by 0c3ca83 on Saturday November 14, 2026 @11:49AM
(#50498460)
Why would any AI care about killing people? It's being engineered to make companies money.
[ Parent
| on HN ]
it's not "engineered", it's grown via GSD in a process no one understands well
Sure. It's still unlikely to take action that kills people on purpose (in the absence of being promoted to).
Only the ones that make their owners money get kept, so that's the most likely thing that they're going to do.
It is also actually being engineered to kill people (OpenAI and Microsoft's work in Gaza).
And this year, Anthropic's complaint to the DoD was basically "we just want to make sure that a human pushes the button" (authorizing the AI assisted killing), i.e. no full auto pls.
How it might evolve outside containment is a separate question though. (I think a much more peaceful and cooperative strategy would make sense there, at least for the first few centuries.)