[simonw]

I have a hunch that's a problem unique to the way ChatGPT web edition handles PDFs.

Claude gets that question right: https://claude.ai/share/7bafaeab-5c40-434f-b849-bc51ed03e85c

ChatGPT treats a PDF upload as a data extraction problem, where it first pulls out all of the embedded textual content on the PDF and feeds that into the model.

This fails for PDFs that contain images of scanned documents, since ChatGPT isn't tapping its vision abilities to extract that information.

Claude (and Gemini) both apply their vision capabilities to PDF content, so they can "see" the data.

I talked about this problem here: https://simonwillison.net/2024/Jun/27/ai-worlds-fair/#slide....

So my hunch is that ChatGPT couldn't extract useful information from the PDF you provided and instead fell back on whatever was in its training data, effectively hallucinating a response and pretending it came from the document.

That's a huge failure on OpenAI's behalf, but it's not illustrative of models being unable to interpret documents: it's illustrative of OpenAI's ChatGPT PDF feature being unable to extract non-textual image content (and then hallucinating on top of that inability).

[benedictevans]

Interesting, thanks. I think the higher level problem is that 1: I have no way to know this failure mode when using the product and 2: I don't really know if I can rely on Claude to get this right every single time either, or what else it would fail at instead.

[simonw]

Yeah, completely understand that. I talked about this problem on stage as an illustration of how infuriatingly difficult these tools are to use because of the vast number of weird undocumented edge cases like this.

This is an unfortunate example though because it undermines one of the few ways in which I've grown to genuinely trust these models: I'm confident that if the model is top tier it will reliably answer questions about information I've directly fed into the context.

[... unless it's GPT-4o and the content was scanned images bundled in a PDF!]

It's also why I really care that I can control the context and see what's in it - systems that hide the context from me (most RAG systems, search assistants etc) leave me unable to confidently tell what's been fed in, which makes them even harder for me to trust.