News for hackers. Stuff that matters.
Re:Agentic Misalignment: How LLMs could be insider threats by cnames on Saturday June 21, 2025 @09:32AM (#44337466)
> Never use AI to do atomonous work

> having them do atomonous work is short sighted

I also think they shouldn’t be doing atomonous work. Maybe autonomous work, but never atomonous.

Re:Agentic Misalignment: How LLMs could be insider threats by cwmoore on Saturday June 21, 2025 @01:14PM (#44339114)
accidentally a word
Re:Agentic Misalignment: How LLMs could be insider threats by cnames on Saturday June 21, 2025 @02:52PM (#44339829)
0 days without a word accident
Re:Agentic Misalignment: How LLMs could be insider threats by cwmoore on Saturday June 21, 2025 @07:52PM (#44341604)
Autumn mango futures soar like terrodactyls.