Re:CaMeL: Defeating Prompt Injections by Design
by simonw on Tuesday April 22, 2025 @10:04AM
(#43762338)
> Do you think that this practically limits the usefulness of an LLM "agent"?
Yes, I do. I think it limits the usefulness a lot. Sadly it's the best option we've seen in 2.5 years for building AI "agents" that don't instantly leak your private data to anyone who asks them for it.
I'd love it if someone could come up with something better!
Yes, I do. I think it limits the usefulness a lot. Sadly it's the best option we've seen in 2.5 years for building AI "agents" that don't instantly leak your private data to anyone who asks them for it.
I'd love it if someone could come up with something better!