The limits of our language-based benchmarks are the limits of our language.| seantrott.substack.com
LLM failures to reason, as documented in Apple’s Illusion of Thinking paper, are really only part of a much deeper problem| garymarcus.substack.com
How do VLMs combine their modalities?| seantrott.substack.com
Modern language models predict "tokens", not words—but what exactly are tokens?| seantrott.substack.com