Framework
CaMeL
An agent architecture proposed by Google DeepMind that splits an AI system into a privileged agent that plans actions and a quarantined agent that processes untrusted input, tracking tainted data so that only high-risk actions require human approval, as a structural mitigation for prompt injection.
CaMeL
2 visible of 2 connections
Episodes2
Related Practices13
Ask about this framework
Transcript mentions
… There was a paper that Google DeepMind put out a couple of years ago, the the camel paper um which proposed a me way of building one of these agents that didn't assume that you can fix prompt injection. And their solution was that th...
… Unless you use a technique like CAMEL and basically, so CAMEL's out of Google and basically what CAMEL says is, "Hey, depending on what the user wants, we might be able to restrict the po...
Framework
CaMeL
An agent architecture proposed by Google DeepMind that splits an AI system into a privileged agent that plans actions and a quarantined agent that processes untrusted input, tracking tainted data so that only high-risk actions require human approval, as a structural mitigation for prompt injection.
Episodes2
Related Practices13
Ask about this framework
Transcript mentions
… There was a paper that Google DeepMind put out a couple of years ago, the the camel paper um which proposed a me way of building one of these agents that didn't assume that you can fix prompt injection. And their solution was that th...
… Unless you use a technique like CAMEL and basically, so CAMEL's out of Google and basically what CAMEL says is, "Hey, depending on what the user wants, we might be able to restrict the po...