This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
Simon Willison
simonwillison.net
did:plc:kft6lu4trxowqmter2b6vg6z
I built a new LLM plugin that can turn a PDF into an image-per-page for feeding into vision models, and in testing it found that GPT-4.1 mini hallucinates WILDLY if you feed it a blank white rectangle followed by a blank black rectangle https://simonwillison.net/2025/May/18/llm-pdf-to-images/
2025-05-18T20:59:31.443Z