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 45 points 8 months ago (27 children)

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) (21 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

[–] eskuero@lemmy.fromshado.ws 12 points 8 months ago* (last edited 8 months ago)

This was hilarious lol

load more comments (20 replies)

load more comments (25 replies)

load more comments (29 replies)