The difference between prompt injection and other categories of security vulnerability is that we can fix other categories of security vulnerability.
If there's a hole in SQLite it's because someone made a mistake. That mistake can then be identified and fixed.
Prompt injection isn't a mistake: it's LLMs doing exactly what they are designed to do, which is to generate a completion based on the tokens that have been passed to them.
If there's a hole in SQLite it's because someone made a mistake. That mistake can then be identified and fixed.
Prompt injection isn't a mistake: it's LLMs doing exactly what they are designed to do, which is to generate a completion based on the tokens that have been passed to them.