Viewing profile — bcampbell88

I think the harness determines how you inspect reasoning. Sometimes it self-exfiltrates into the user response. This would be a touchy topic for Anthropic because this distilled re…

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 deterministi…

https://www.vaibot.io/blog/prompt-injection-is-an-egress-pro...