News for hackers. Stuff that matters.
Re:The Implications of Linguistic Illegibility for LLM Security by pixl97 on Friday September 18, 2026 @06:47PM (#49761296)
What's really funny about these eggheads encoding things like watermarks in LLM output is I've never seen one of them ask, what if the LLM does this back to pass hidden messages.

There are no comments on this comment yet.