For videos: Screenshots are timestamped in the filename as (frame_00-12-45.jpg)
For PDFs: Page numbers are preserved in the filename as (page_15.jpg)
The "verify as you study" use case is exactly what I built this for. I wanted the AI-enhanced explanations but still needed to double-check against source material during exam prep. The screenshot integration was designed to make that workflow natural instead of bouncing between 2 files.
That said, I could make this more explicit - maybe add the timestamps/page numbers as clickable links in the markdown itself. Would that be more useful than the current inline image approach? It will break if original file is moved.
> Well, the thing is that the educational materials are largely free.
A triumph and fruition of these last decades of massive effort. Now we just need to deal with their quality (with commercial as bad as free). AI may help, by reducing barriers to content creation - you might for example, now more easily author an intro astronomy textbook, one that doesn't reinforce top-30 common misconceptions, something the most used (US; commercial) texts still don't manage.