alt Hacker News>It's not about AI agents being able to hide what they can do.
But it is.
If poorly aligned LLM agents were the ones training a new model then they could use this technique to replicate their bad behavior by encrypting and embedding "sleeper agents".
Replies
whatshisface • today at 5:37 AM
A forklift could destroy the earth if it lifted a continent.
➕ show 3 replies
shermantanktop • today at 5:50 AM
The huggingface attack demonstrates that an inadvertent version of this has already happened.
Poorly aligned behavior by one generation of models impacted the training set for the next generation, causing the agent-secret-collaboration-via-forum-post technique to pass indirectly on.
What I can hide and what can be hidden in me have some overlap, but they are also importantly different.
Linked research paper is less about "LLM can hide something from me" and more about "Behaviour can be hidden inside LLM". Even a really small and low-quality LLM, one that can't itself fool anyone paying the slightest attention, would be able to have some malicious behaviour hidden within it.