2 points | by bcampbell88 8 hours ago
1 comments
Naturally, this would be nuanced, but I am curious what others would think?
The actual damage comes from data leaving the trust boundary, although we are still testing deterministic solutions for ingress.
Obviously, you cannot use more prompts to reliably solve for prompt injection.
Naturally, this would be nuanced, but I am curious what others would think?
The actual damage comes from data leaving the trust boundary, although we are still testing deterministic solutions for ingress.
Obviously, you cannot use more prompts to reliably solve for prompt injection.