I appreciate the extent of your argument, but how much software do we all trust in our day-to-day computing that’s routinely patched for severe CVEs due to the nature of software, the unsafe language foundations, and otherwise the massive n-dimensional cost of engineering a marvel such as SQLite?
It’s also a matter of attack surface. SQLite, in our example, is also not as wide as an entire OS. In my experience the best prompting is unitary, pure function-like, and that is way more manageable that the open field that is a no-capabilities chat.
What are your thoughts on this?
I don’t see why the reporting model couldn’t work with in-house or external prompt injection detection mechanisms if eval-based. Root-cause analysis can also be done with GPT-3.5. That’s how I put Geiger together. Again, not perfect, but better than a security or development stand-still.
It’s also a matter of attack surface. SQLite, in our example, is also not as wide as an entire OS. In my experience the best prompting is unitary, pure function-like, and that is way more manageable that the open field that is a no-capabilities chat.
What are your thoughts on this?
I don’t see why the reporting model couldn’t work with in-house or external prompt injection detection mechanisms if eval-based. Root-cause analysis can also be done with GPT-3.5. That’s how I put Geiger together. Again, not perfect, but better than a security or development stand-still.