PDF to vision with gpt 4.1
2025-05-19 18:28:33.616021+02 by Dan Lyke 0 comments
Simon Willison @simon@simonwillison.net
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/