News for hackers. Stuff that matters.
Re:Agentic Misalignment: How LLMs could be insider threats by DennisP on Saturday June 21, 2025 @12:01PM (#44338544)
If this paper is right, then you might at first be outraced by a competitor using autonomous AI, but only until that competitor gets stabbed in the back by its own AI.
Re:Agentic Misalignment: How LLMs could be insider threats by bluefirebrand on Saturday June 21, 2025 @12:10PM (#44338619)
Which unfortunately might still be long enough for them to sink your business

And their customers won't care either way it seems

Or if they do care they won't have any real ability to do anything about it anyways

Re:Agentic Misalignment: How LLMs could be insider threats by DennisP on Saturday June 21, 2025 @12:34PM (#44338826)
Maybe. The backstabbing rate is unknown so far. If it's high enough, then autonomy will be poor strategy.
Re:Agentic Misalignment: How LLMs could be insider threats by econ on Saturday June 21, 2025 @04:47PM (#44340622)
It might be the trigger :)