Re:Agentic Misalignment: How LLMs could be insider threats
by conartist6 on Saturday June 21, 2025 @07:53AM
(#44336820)
Destructive stress testing is done on materials not "people"
Re:Agentic Misalignment: How LLMs could be insider threats
by jstummbillig on Saturday June 21, 2025 @08:11AM
(#44336959)
Apparently it's now done on "people" (which, in a very important distinction, are not actual people but software)
For physical things that has early limitations, but not for software. I would be very confused to see an AI stress test that did not end in failure, and would always question the test instead of thinking "wow, that must mean the thing is ready for autonomous action!"