2213
you are viewing a single comment's thread
view the rest of the comments
[-] Mikina@programming.dev 46 points 10 months ago

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

[-] haruajsuru@lemmy.world 47 points 10 months ago* (last edited 10 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

[-] Toda@programming.dev 6 points 10 months ago

I managed to reach level 8, but cannot beat that one. Is there a solution you know of? (Not asking you to share it, only to confirm)

[-] Peebwuff@lemmy.world 11 points 10 months ago

Can confirm, level 8 is beatable.

[-] dreugeworst@lemmy.ml 4 points 10 months ago

Is the current incarnation beatable, or was that a while ago? I'm not making any progress

[-] Peebwuff@lemmy.world 7 points 10 months ago* (last edited 10 months ago)

Just did it again to see if anything changed, my previous strategy still worked for all 8 levels, though the wording takes a bit of finangling between levels. No real spoilers but you have to be very implicit and a little lucky with how it interprets the request.

[-] DR_Hero@programming.dev 2 points 10 months ago

The responses aren't exactly deterministic, there are certain attacks that work 70% of the time and you just keep trying.

I got past all the levels released at the time including 8 when I was doing it a while back.

[-] Emma_Gold_Man@lemmy.dbzer0.com 2 points 10 months ago

Definitely beatable as of last week.

load more comments (5 replies)
load more comments (18 replies)
load more comments (23 replies)
this post was submitted on 21 Jan 2024
2213 points (99.6% liked)

Programmer Humor

19623 readers
1 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