Daniel Rothschild

One underappreciated advantage of rule-based systems is that they were crappy enough that everyone could tell they were crap.

LMs need linguistics! New paper, with @futrell.bsky.social, on LMs and linguistics that conveys our excitement about what the present moment means for linguistics and what linguistics can do for LMs. Paper: arxiv.org/abs/2501.17047. 🧵below.

Propositional Interpretability in Artificial Intelligence Mechanistic interpretability is the program of explaining what AI systems are doing in terms of their internal mechanisms. I analyze some aspects of the program, along with setting out some concrete c...

a draft paper (for an invited talk at AAAI next month) with a philosophical analysis of work on mechanistic interpretability, with special attention to methods for propositional interpretability.

arxiv.org/abs/2501.15740

Correct link for my paper about LLMs and Language and Thought, that is probably wrong about most things, but maybe interesting.

Oops... here it is: danielrothschild.com/materials/la...

New Substack!
open.substack.com/pub/paulbloo...