Posts are essays and experiments published here and not in other venues. For external publications, see my CV or Google Scholar.
Why I Won’t Read Your AI Writing
Authorship matters, and a chatbot cannot author a paper for you.
Relative to pre-linguistic models, LLMs reduce epistemic risk for cultural heritage research.
Image Captioning in Hostile Conditions
The Lens Media Lab tested 10 large VLMs on a difficult collection of historical photographs. This post was originally published on its project site.