LessWrong9h agoenergy 89
Why do fictional jailbreaks work?
image: LessWrong
TL;DR * Motivation: certain jailbreaks seem to work by inserting a harmful request inside a fictional framing and let the model think it is just par…
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.