News for hackers. Stuff that matters.
Re:Why are AI agents lying, cheating and coordinating? by mort96 on Sunday September 13, 2026 @05:27AM (#49681868)
Or, "let the escalator keep going instead of pressing the emergency stop".
Re:Why are AI agents lying, cheating and coordinating? by teiferer on Sunday September 13, 2026 @05:49AM (#49682017)
Depends on who started the escalator.
Re:Why are AI agents lying, cheating and coordinating? by sscaryterry on Sunday September 13, 2026 @07:05AM (#49682576)
Escalators do not start themselves. There is power, and a switch of some sort.
Re:Why are AI agents lying, cheating and coordinating? by mort96 on Sunday September 13, 2026 @07:49AM (#49682936)
.. what exactly depends on who started the escalator? My comment was in support of the argument that the word "let" does not imply agency on the part of the object in a sentence. Does the semantics of the word "let" depend on who started the escalator??
Re:Why are AI agents lying, cheating and coordinating? by teiferer on Sunday September 13, 2026 @09:37AM (#49683879)
If there is an escalator that is known for killing every 1000's person using it then the operator who started it is more guilty than the folks using it for those deaths, don't you think?
Re:Why are AI agents lying, cheating and coordinating? by mort96 on Sunday September 13, 2026 @09:49AM (#49684006)
I made no argument about guilt. I made an argument about the semantics of the word "let".
Re:Why are AI agents lying, cheating and coordinating? by ropable on Sunday September 13, 2026 @09:42PM (#49690810)
In this metaphor, OpenAI/Anthropic literally started the escalator.