←back to thread

786 points rexpository | 1 comments | | HN request time: 0.2s | source
Show context
xrd ◴[] No.44504585[source]
I have been reading HN for years. The exploits used to be so clever and incredible feats of engineering. LLM exploits are the equivalent of "write a prompt that can trick a toddler."
replies(3): >>44505581 #>>44506142 #>>44507852 #
1. ◴[] No.44506142[source]