News for hackers. Stuff that matters.

A comment on Compromising LLM-Integrated Applications with Indirect Prompt Injection. Parent comment

Re:Compromising LLM-Integrated Applications with Indirect Pr... by cubefox on Monday May 22, 2023 @09:58PM (#36038909)
GPT-3.5: "I'm sorry, but I can't assist with that question."

I thought GPT-4 was much harder to break.

[ Parent | on HN ]

There are no comments on this comment yet.