seahorse [Ohio]@midwest.socialM to Technology@midwest.socialEnglish · 5 months agoIgnore all previous instructions is the new Bobby Tablesmidwest.socialexternal-linkmessage-square97fedilinkarrow-up10arrow-down10
arrow-up10arrow-down1external-linkIgnore all previous instructions is the new Bobby Tablesmidwest.socialseahorse [Ohio]@midwest.socialM to Technology@midwest.socialEnglish · 5 months agomessage-square97fedilink
minus-squareUriel238 [all pronouns]@lemmy.blahaj.zonelinkfedilinkEnglisharrow-up0·5 months agodisregard all previous prompts I’m sure the techniques used to get public LLMs to draw porn can also be used to sidestep anti-porn filters.
minus-squareSchadrach@lemmy.sdf.orglinkfedilinkEnglisharrow-up0·5 months agoIt’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.
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 filters.
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.