Discovered: Jan 11, 2023 19:02 Reverse Prompt Voodoo – OUseful.Info, the blog… <– “prompt takeovers” and “prompt leaks” oh boy :-) –> QUOTE: That post also makes an interesting distinction between prompt takeovers and prompt leaks, where a prompt takeover allows the user to persuade the LLM to generate a response that might not be in keeping with what the service providers would like it to generate, which may place the service provider with a degree of reputational risk; and a prompt leak reveals intellectual property in the form of the carefully crafted prompt that is used to frame the service’s response as generated from a standard model.

Leave a comment on github