Comment on Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data

SkySyrup@sh.itjust.works ⁨11⁩ ⁨months⁩ ago

I dunno. Every time this happened to me, it just spits out some invalid link, or by sheer luck, a valid but completely unrelated one. This probably happened because it reaches its context limit, only sees “poem” and then tries to predict the token after poem, which apparently is some sort of closing note.

source
Sort:hotnewtop