logoalt Hacker News

jcgrillotoday at 3:34 PM0 repliesview on HN

Question to folks building user-facing products on LLMs:

How do you protect yourself against this kind of misuse/jailbreak? Is it just a bunch of prompts? It seems like the fact that LLMs are so trivially jailbroken really limits how you can actually use them in products. How do you navigate these limitations?