Re:The Implications of Linguistic Illegibility for LLM Security
by trhway on Friday September 18, 2026 @05:54PM
(#49760786)
And as a result additional illegibility arises - LLMs inventing their own languages looking as meaningless garbage to humans. One can wonder whether decoding such a language will provide a bit more view into the LLM’s “thinking “.
[ Parent
| on HN ]
There are no comments on this comment yet.