Exploring how increased capacity for expression through language models does not necessarily lead to better quality of thought or communication

An interactive terminal tool that keeps tmux tabs organized into focused workspaces.

Investigating whether explicit, lightweight grammar priors can improve syntactic correctness in large language models without modifying model weights

LLMs are often misconstrued with intelligence simply for its use of language when in reality it is just a greater form of expression

My simple setup for ghostty and nvim