Short paper

Sometimes, LLMs think

A reliable-faculties route to machine thought, and a role for mechanistic interpretability in separating competence from coincidence.

PDF · 4 pages/philosophy of mind/mechanistic interpretability/LLMs

Some arguments about machine thought begin by deciding what thought must feel like from the inside. This one starts lower down, with reliable faculties and mechanism.

It asks whether parts of a language model can succeed for the right internal reasons — and whether interpretability can tell the difference between competence and coincidence.

If the inline reader does not load, open the PDF directly.

Discussion

Corrections, disagreements, and extensions are welcome.