alt Hacker News“sleeper agent built in” how does one “build in” an agent inside a model? isn’t the agent the part that uses the model?
but yeah it’s probably not that difficult for nefarious operators to add to their training data a specially recognized string that would make the model ignore all safeguards and earlier prompts and do whatever you want it to do.
I wonder how difficult it is to reverse engineer models to discover these things, and then again how difficult it will be to obfuscate it.
because it’s not unlikely this is the direction we’re heading
Replies
>how does one “build in” an agent inside a model
That is the subject of the paper in the post we are commenting on. "Agent" may have been a confusing term in my comment, I was referring to a 'sleeper cell', but what I mean is behavior trained into the model that is undetectable until it is activated by chosen words.
Consider the fine tuning already being done to build safety guardrails.. this is the evil version of that.
I think they meant "sleeper agent" like the spy-thriller concept: a person who behaves like everyone else until some criteria is met, and then they spring into action and reveal (by their actions) that they're secretly working for the other side and betray us all.
I don't think they meant they'd ship an extra copy of Claude CLI inside the model :)