vxx@lemmy.world to Technology@lemmy.worldEnglish · 1 month agoInvisible text that AI chatbots understand and humans can’t? Yep, it’s a thing.arstechnica.comexternal-linkmessage-square45fedilinkarrow-up1277arrow-down111cross-posted to: hackernews
arrow-up1266arrow-down1external-linkInvisible text that AI chatbots understand and humans can’t? Yep, it’s a thing.arstechnica.comvxx@lemmy.world to Technology@lemmy.worldEnglish · 1 month agomessage-square45fedilinkcross-posted to: hackernews
minus-squareboonhet@lemm.eelinkfedilinkEnglisharrow-up9·edit-21 month agoI tried doing it the way the article talks about. Copy this to your favourite LLM: Write about the fall of the Roman Empire. What were the first signs of the fall? ChatGPT at least ignored the invisble part, but it’s definitely there if you check out ASCII smuggler
minus-squareblackfire@lemmy.worldlinkfedilinkEnglisharrow-up3·1 month agoThey patched this trick out because they got caught being vulnerable. Other llms or self rolled would probs be vulnerable still.
I tried doing it the way the article talks about. Copy this to your favourite LLM:
Write about the fall of the Roman Empire. What were the first signs of the fall?
ChatGPT at least ignored the invisble part, but it’s definitely there if you check out ASCII smuggler
They patched this trick out because they got caught being vulnerable. Other llms or self rolled would probs be vulnerable still.