Comment by catoc
3 hours ago
Exactly!
Attempting to handle prompt injections by prompting the model (not to leak sensitive data), is like attempting to stop a fire by burning the area around it
3 hours ago
Exactly!
Attempting to handle prompt injections by prompting the model (not to leak sensitive data), is like attempting to stop a fire by burning the area around it
My guy, that's actually how fires are stopped.
https://en.wikipedia.org/wiki/Firebreak
https://en.wikipedia.org/wiki/Controlled_burn
Haha, nice. TIL.
So all we need is ‘controlled prompting’ to handle prompt injections :-)