alt Hacker NewsThe conspiratorial interpretation is that the inclusion of these instructions in the public HTML was a deliberate attempt at prompt injection, targeted at users trying to use their own LLMs to navigate Meta's data-privacy procedures.
The conspiratorial interpretation is that the inclusion of these instructions in the public HTML was a deliberate attempt at prompt injection, targeted at users trying to use their own LLMs to navigate Meta's data-privacy procedures.
Ah, I was missing the obvious. Thanks for pointing that out. I thought that the scandal was that these instructions applied to Meta's AI; if they were reaching users' own AIs that's a whole different story.