News for hackers. Stuff that matters.
Re:AI Models Like GPT-4o Change Without Warning. Here's What... by aickin on Wednesday February 19, 2025 @04:17PM (#43107803)
Yep, that's also a huge issue with LLMs in production. Our product has some automatic detection of jailbreak attempts so that you can see when people are trying to jailbreak & prompt inject, but hallucinations are the biggest unsolved problem imo.

There are no comments on this comment yet.