The LLM is reading the bytes of the file, not looking at a picture of its rendering. File metadata exists as well, and change history. Tons of places to hide text.
Even if you processed it via a screenshot, image files are processed byte by byte as well and can contain textual metadata.
Is it? I thought it was making chunks that consist of 2-3 words, assigning coordinates and weights to them, and performing fancy maths and statistics with them. I wouldn’t have thought the binary data would be particularly useful in that effort?
I’m just a sysadmin with very little in the way of higher maths or computer science under my belt, so I genuinely don’t know how “correct” my mental model of things are.
Even if you processed it via a screenshot, image files are processed byte by byte as well and can contain textual metadata.