Finnegans Wake has extremely high Shannon entropy; frontier models extremely low
Surprising: frontier models (Claude, ChatGPT, Deepseek V4) produce the most predictable text of any local AI model or human text I’ve ever tested.
Not surprising: Finnegans Wake is off the charts, by far least predictable—Shannon & Lydia Liu proved right—and Hemingway the most predictable human.


Quoting Aligned models have less information/entropy than Shannon measured for English.
Part of Libidinal Language Models.
Originally posted on Bluesky.