flâneur — a map of the web's best reading

You can’t solve AI security problems with more AI

simonwillison.net · 1,642 words · saved by 1 readers

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 …

You can’t solve AI security problems with more AI Simon Willison’s Weblog Subscribe Sponsored by: Atlassian - Give your agents a plan. Not a prompt. New Jira capabilities unlock full-context for AI-native software development. Assign tasks to Claude, Cursor, or GitHub Copilot, now directly from Jira. Learn more You can’t solve AI security problems with more AI 17th September 2022 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 this instead”) is t

Explore this link on the map →

related reading