News for hackers. Stuff that matters.

A comment on Frontier AI agents violate ethical constraints 30–50% of time, pressured by KPIs. Parent comment

Re:Frontier AI agents violate ethical constraints 30–50% of ... by phkahler on Tuesday February 10, 2026 @09:59AM (#46960533)
If you want absolute adherence to a hierarchy of rules you'll quickly find it difficult - see I,Robot by Asimov for example. An LLM doesn't even apply rules, it just proceeds with weights and probabilities. To be honest, I think most people do this too.
[ Parent | on HN ]
Re:Frontier AI agents violate ethical constraints 30–50% of ... by jayd16 on Tuesday February 10, 2026 @11:54AM (#46962791)
You're using fiction writing as an example?
[ Parent | on HN ]
Re:Frontier AI agents violate ethical constraints 30–50% of ... by phkahler on Tuesday February 10, 2026 @01:48PM (#46964862)
>> You're using fiction writing as an example?

Sure. The examples in those stories illustrate how a small set of rules can quickly come into conflict with one another. Not that the stories are real, but the interpretations of the rules are understandable and the consequences are comprehensible without too much complexity.

[ Parent | on HN ]