Feedback Coding Enables Inference-Time Covert Agentic Communication
Researchers show black-box LLMs can hide messages in generated text with near-zero decoding error.
1 stories, newest first · one card per story
Researchers show black-box LLMs can hide messages in generated text with near-zero decoding error.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views