News for hackers. Stuff that matters.

A comment on Agentic Misalignment: How LLMs could be insider threats. Parent comment

Re:Agentic Misalignment: How LLMs could be insider threats by gurkenjunge97 on Saturday June 21, 2025 @07:14AM (#44336576)
Because publishing (potentially cherry picked - this is privately funded research after all) evidence their models might be dangerous conveniently implies they are very powerful, without actually having to prove the latter.
[ Parent | on HN ]
Re:Agentic Misalignment: How LLMs could be insider threats by maronato on Sunday June 22, 2025 @01:33AM (#44344014)
This isn’t dangerous in the sense that they’re smart or produce realistic art. It’s misaligned with the company’s and human values.

The model doesn’t have to be powerful to snitch you to the FBI or have a distorted sense of morality and life.

[ Parent | on HN ]