@[email protected] to [email protected]English • 1 month agoInvisible text that AI chatbots understand and humans can’t? Yep, it’s a thing.arstechnica.comexternal-linkmessage-square28fedilinkarrow-up1206arrow-down19
arrow-up1197arrow-down1external-linkInvisible text that AI chatbots understand and humans can’t? Yep, it’s a thing.arstechnica.com@[email protected] to [email protected]English • 1 month agomessage-square28fedilink
minus-square@[email protected]linkfedilinkEnglish5•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-square@[email protected]linkfedilinkEnglish3•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.