Saltiness aside, it's a good paper! Digs into the question at the heart of prompt injection: can we safely separate instructions from inout in an LLM?
Paper Analyzes Prompt Injection: Separating Instructions from Input
By
–
By
–
Saltiness aside, it's a good paper! Digs into the question at the heart of prompt injection: can we safely separate instructions from inout in an LLM?