Research
Study finds frontier language models overuse patterns that are hard for humans to read
Researchers from New York University and the University of Texas at Austin identify six linguistic patterns that frontier models overuse. They attribute the problem to training on code and math, where correctness is rewarded but clarity is not, while smaller models write more like humans.
Every outlet that ran it 1 article
The DecoderTech pressLead
Researchers find six patterns that make AI text so exhausting to read