Comment by qingcharles
4 hours ago
Sadly nothing in Scott's blog post about how they obtained the source. Was it still in Microsoft's archives? Did they happen upon some tractor-feed print-outs they had to type in by hand?
4 hours ago
Sadly nothing in Scott's blog post about how they obtained the source. Was it still in Microsoft's archives? Did they happen upon some tractor-feed print-outs they had to type in by hand?
It would also be interesting why it was open-sourced now. I assume if they had done the same last year, the resulting loss of revenue would not have destroyed the plucky little $3T upstart.
I assume today typing in by hand is no longer needed, with text parsing from images being table stakes for LLMs.
You don’t need an llm to do this.
Of course, but I do know that it wasn't that long ago that OCR still wasn't great for many documents. These days LLMs can tackle it all.