AI brief
A LessWrong post argues that when users interact with frontier models, their prompts can include not just the words on the page but also much of what they have publicly written online.
Written by AI from LessWrong's published text.
Source
“TL;DR: Increasingly when you interact with frontier models, your prompt doesn't only contain the words on the page, but also a lot of what you've ever publicly written online. This is not intended to be a scary post.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗