I've not followed the literature very closely for some time - what problem are they trying to solve in the first place? They write "for documents to be effectively used in RAG pipelines, they must be split into smaller, semantically meaningful chunks". Segmenting each page by paragraphs doesn't seem like a particularly hard vision problem, nor do I see why an OCR system would need to incorporate an LLM (which seem more like a demonstration of overfitting than a "language model" in any literal sense, going by ChatGPT). Perhaps I'm just out of the loop.
Finally, I must point out that statements in the vein of "Why [product] 2.0 Changes Everything" are more often than not a load of humbug.
Large hard drives and fast internet do not render obsolete the principle of frequency domain compression. MP3 and JPG will probably remain in service for a very long time.
But of course, if people weren't habituated to this bogus conception of obsolescence, how on earth would Microsoft manage to sell them a word processor for $179.00?
They don't. You now subscribe to Copilot 365 or whatever the hell Office is called today for the low, low price of $12.99 per month for the rest of your life.
I'm sure that's also an option but I'm looking at their website right now and it says I can own this warmed-over text editor outright for 179$. What a bargain.
"Pay less attention, otherwise you might become apathetic." Granted, mass media is generally slop (this article being no exception), but that's all the more reason one should observe and think carefully.
Doesn't that seem a bit too complacent? Personally I've always thought the opposite - malcontents have more to gain and less to lose by criticizing or opposing the status quo.
You would have been right when the ratio of malcontents to those who could say that they enjoyed the benifits of society was 5 or 10 to 1
but tose days are gone, and in many geographic (read postal codes) locations, there is nothing to be contented with or strive for, except at worse than lightnigng strike while winning the lottery odds.
Finally, I must point out that statements in the vein of "Why [product] 2.0 Changes Everything" are more often than not a load of humbug.