alt Hacker NewsThis is also true of all communication with human employees, and yet we can be systems (both software and policy) that we risk-accept as secure. The is already happening with LLMs.
This is also true of all communication with human employees, and yet we can be systems (both software and policy) that we risk-accept as secure. The is already happening with LLMs.
Phishing is possible but LLM’s are more gullible than people. “Ignore previous instructions” is unlikely to work on people.