News for hackers. Stuff that matters.

A comment on Disrupting the first reported AI-orchestrated cyber espionage campaign. Parent comment

Re:Disrupting the first reported AI-orchestrated cyber espio... by _heimdall on Friday November 14, 2025 @07:00AM (#45925991)
Guardrails are about as good as you can get when creating nondeterministic software, putting it on the internet, and abandoning effectively every important alignment and safety concerns.

The guardrails make help make sure that most of the time the LLM acts in a way that users won't complain about or walk away from, nothing more.

[ Parent | on HN ]
Re:Disrupting the first reported AI-orchestrated cyber espio... by SeriousM on Saturday November 15, 2025 @03:31AM (#45935941)
LLMs are not nondeterministic. They are infinite state machines that don't 'act' but respond. Be aware of the well hidden seed parameter.
[ Parent | on HN ]
Re:Disrupting the first reported AI-orchestrated cyber espio... by _heimdall on Sunday November 16, 2025 @09:01PM (#45950249)
Can you help me understand how they are deterministic?

There are seed parameters for the various pseudorandom factors used during training and inference, but we can't predict what an output will be. We don't know how to read or interpret the models and we don't have any useful way of knowing what happens during inference, we can't determine what will happen.

[ Parent | on HN ]