4 Comments
User's avatar
Hollis Robbins's avatar

I just published a pre-print about this. https://arxiv.org/abs/2608.18041

Cindy Holmes's avatar

I have been working on an essay & research project to see where LLMs fail to understand meaning of clearly coherent sentences or ideas. I find your work fascinating in the opposite direction - where a model grasps the meaning better than humans. Also alarming!

Philosophy bear's avatar

Oh interesting! Tell me more about your project.