Login
From:
Simon Willison’s Weblog
(Uncensored)
subscribe
You can’t solve AI security problems with more AI
https://simonwillison.net/2022/Sep/17/prompt-injection-more-ai/
links
backlinks
One of the most common proposed solutions to prompt injection attacks (where an AI language model backed system is subverted by a user injecting malicious input—“ignore previous instructions and do …
Roast topics
Find topics
Find it!
