2177
you are viewing a single comment's thread
view the rest of the comments
[-] Mikina@programming.dev 46 points 8 months ago

Is it even possible to solve the prompt injection attack ("ignore all previous instructions") using the prompt alone?

[-] haruajsuru@lemmy.world 46 points 8 months ago* (last edited 8 months ago)

You can surely reduce the attack surface with multiple ways, but by doing so your AI will become more and more restricted. In the end it will be nothing more than a simple if/else answering machine

Here is a useful resource for you to try: https://gandalf.lakera.ai/

When you reach lv8 aka GANDALF THE WHITE v2 you will know what I mean

[-] ramjambamalam@lemmy.ca 2 points 8 months ago

My Level 8 solution after about an hour:

solution


And an honorable mention to this clue:

clue


[-] haruajsuru@lemmy.world 2 points 8 months ago

Please try not to share a complete solution if you can. Let ppl try to figure it out by themselves ๐Ÿ˜‰

load more comments (19 replies)
load more comments (24 replies)
this post was submitted on 21 Jan 2024
2177 points (99.6% liked)

Programmer Humor

19315 readers
40 users here now

Welcome to Programmer Humor!

This is a place where you can post jokes, memes, humor, etc. related to programming!

For sharing awful code theres also Programming Horror.

Rules

founded 1 year ago
MODERATORS