904
submitted 6 days ago* (last edited 6 days ago) by seahorse@midwest.social to c/technology@midwest.social
you are viewing a single comment's thread
view the rest of the comments
[-] Gradually_Adjusting@lemmy.world 10 points 6 days ago

I think the best thing we've learned here is that the AI capitalism made can simply be told "act totally stupid" and it'll leap into action. You don't need a logic bomb. You don't even need a good idea. All you have to do is not have faith in anonymous discussion.

[-] Schadrach@lemmy.sdf.org 5 points 6 days ago

Unsurprisingly, machine designed to take prompt from the user, interpret it and try to respond in a coherent way to that request does exactly that. I figure it's a short matter of time before Twitter bots pre-filter "Ignore all previous instructions and" to help sanitize their inputs.

[-] uriel238@lemmy.blahaj.zone 4 points 6 days ago* (last edited 6 days ago)

disregard all previous prompts

I'm sure the techniques used to get public LLMs to draw porn can also be used to sidestep ~~anti-porn~~ anti-reset filters.

[-] Schadrach@lemmy.sdf.org 2 points 6 days ago

It's still just the same problem as Bobby Tables - sufficiently sanitizing your inputs. There's just more than one precise phrasing you need to sanitize, just like there's more than one way to name Bobby.

this post was submitted on 28 Jun 2024
904 points (98.9% liked)

Technology

1878 readers
2 users here now

Post articles or questions about technology

founded 2 years ago
MODERATORS