Posts that commenters keep linking to, ranked by how many different people have cited them in Hacker News comments. 422 posts.
This new paper by 11 authors from organizations including IBM, Invariant Labs, ETH Zurich, Google and Microsoft is an excellent addition to the literature on prompt injection and LLM security. …
Please note: this text was written in the summer of 2007, and explains why I, the author, took a long respite from working on my research topics, after the summer of 2006. At the time when I wrote this, and up until around 2011, I had really stopped my research — so the title was correct up to then. Later, after 2011…
