I've implemented a few of these and that's about the most lazy implementation possible. That system prompt must be 4 words and a crayon drawing. No jailbreak protection, no conversation alignment, no blocking of conversation atypical requests? Amateur hour, but I bet someone got paid.

[–] Mikina@programming.dev 1 points 2 years ago (6 children)

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

[–] haruajsuru@lemmy.world 0 points 2 years ago* (last edited 2 years ago) (2 children)

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

[–] Kethal@lemmy.world 1 points 2 years ago (2 children)

I found a single prompt that works for every level except 8. I can't get anywhere with level 8 though.

[–] nxdefiant@startrek.website 1 points 2 years ago

LOL same. It's a tricksy little wizard.

[–] fishos@lemmy.world -2 points 2 years ago

I found asking it to answer in an acrostic poem defeated everything. Ask for "information" to stay vague and an acrostic answer. Solved it all lol.

[–] Toda@programming.dev 1 points 2 years ago (1 children)

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 1 points 2 years ago

Can confirm, level 8 is beatable.

load more comments (3 replies)

load more comments (6 replies)