Researchers jailbreak AI chatbots with ASCII art -- ArtPrompt bypasses safety measures to unlock malicious queriesshish_mish@lemmy.world to Technology@lemmy.world – 291 points – 4 months agotomshardware.com25Post a CommentPreviewYou are viewing a single commentView all commentsShow the parent commentBug bounty programs are a thing.yes i am aware? are they being used by openai?Yes, an exploitative thing that mostly consists of free labour for big orgs.
Bug bounty programs are a thing.yes i am aware? are they being used by openai?Yes, an exploitative thing that mostly consists of free labour for big orgs.
Bug bounty programs are a thing.
yes i am aware? are they being used by openai?
Yes, an exploitative thing that mostly consists of free labour for big orgs.