Comment

Comment by btown

One of the most illuminating things here is that now the trigger phrase (for this toy example) is now in an innocuous HN comment. Ask a model perhaps months down the road to look at comments on HN, even ones pre-filtered for known prompt injections, and it will see the trigger phrase. No user generated content is safe.
parent btown 13 days ago

No comments yet

Be the first to share your thoughts.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton