AI brief
A LessWrong post asks how frontier LLMs that can generate artistic SVG images would hide a message in an image, and whether such hidden messages could be decoded. The text says it presents results from that experiment.
Written by AI from LessWrong's published text.
Source
“TL;DR Frontier LLMs are now capable of generating artistic images using SVG. We ask – if these LLMs had to hide a message in an image – how would they do so? And if they hid such messages, could they be successfully decoded?”
Interpretation or community commentary rather than straight reporting.
Read original story ↗