381–390 of 456 posts
Earlier quoted context omitted.
How do you handle the privacy of the scanned documents?
We work with fortune 500s in sensitive industries (healthcare, fintech, etc). Our policies are: - data is never shared between customers - data never gets used for training - we also configure data retention policies to auto-purge after a time period
Earlier quoted context omitted.
Software is dead, if it isn't a prompt now, it will be a prompt in 6 months. Most of what we think software is today, will just be a UI. But UIs are also dead.
Software without data moats, vender lock-in, etc sure will. All the low handing fruit saas is going to get totally obliterated by LLM built-software.
B2B is different from B2C, so if one vendor has a handful of clients and they won't switch away, there's no obliterating happening.
What's opened up is even lower hanging fruit, on more trees. A SaaS company charging $3/month for the left-handed underwater basket weaver niche now becomes viable as a lifestyle business. The shovels in this could be supabase/similar, since clients can keep access to their data there even if they change frontends.
We are driving full speed into a xerox 2.0 moment and this time we are doing so knowingly. At least with xerox, the errors were out of place and easy to detect by a human. I wonder how many innocent people will lose their lives or be falsely incarcerated because of this. I wonder if we will adapt our systems and procedures to account for hallucinations and "85%" accuracy. And no, outlawing use the use of AI or increa…
Earlier quoted context omitted.
I'm not suggesting we re-invent RDF or any other kind of semantic web idea. And the fact that semantic data can be stored in a PDF isn't really the problem being solved by tools such as these. In many cases, PDF is used for things like scanned documents where adding that kind of metadata can't really be done manually - in fact the kinds of tools suggested in the post would be useful for adding that metadata to the PD…
I mean, you want to store a kitchen sink of data, too. You don't like the semantic web or semantic metadata, fine - what do you propose? A custom metadata format for each use case? That is semantic information. If you don't do that, you get a kitchen sink. If you need to store 1930s death certificats, 10k filings, your doctor's signup forms, the ARR graph for your startup, and a genealogy chart all in the same format…
PDF is terrible because it has grown over time from a format that was originally made for one purpose into a format that is used for too many purposes. That organic growth has caused PDFs to be very difficult to use for a wide variety of use cases.
That opinion doesn't imply almost anything else that you have claimed I support (and generally do not).
Earlier quoted context omitted.
This is spot on, any legacy vendor focusing on a specific type of PDF is going to get obliterated by LLMs. The problem with using an off-the-shelf provider like this is, you get stuck with their data schema. With an LLM, you have full control over the schema meaning you can parse and extract much more unique data. The problem then shifts from "can we extract this data from the PDF" to "how do we teach an LLM to extra…
> The problem then shifts from "can we extract this data from the PDF" to "how do we teach an LLM to extract the data we need, validate its performance, and deploy it with confidence into prod?" A smart vendor will shift into that space - they'll use that LLM themselves, and figure out some combination of finetunes, multiple LLMs, classical methods and human verification of random samples, that lets them not only "va…
There's definitely space here to help the customer realize their extraction vision because it's still hard to scale this effectively on your own!
I work in fintech and we replaced an OCR vendor with Gemini at work for ingesting some PDFs. After trial and error with different models Gemini won because it was so darn easy to use and it worked with minimal effort. I think one shouldn't underestimate that multi-modal, large context window model in terms of ease-of-use. Ironically this vendor is the best known and most successful vendor for OCR'ing this specific ty…
> Why Gemini 2.0 Changes Everything Clickbait. It doesn't change "everything". It makes ingestion for RAG much less expensive (and therefore feasible in a lot more scenarios), at the expense of ~7% reduction in accuracy. Accuracy is already rather poor even before this, however, with the top alternative clocking in at 0.9. Gemini 2.0 is 0.84, although the author seems to suggest that the failure modes are mostly arou…
In this use-case, accuracy is non-negotiable with zero room for any hallucination. Overall it changes nothing.
Earlier quoted context omitted.
>A smart vendor will shift into that space - they'll use that LLM themselves It's a bit late to start shifting now since it takes time. Ideally they should already have a product on the market.
There's still time. The situation in which you can effectively replace your OCR vendor with hitting LLM APIs via a half-assed Python script ChatGPT wrote for you, has existed for maybe few months. People are only beginning to realize LLMs got good enough that this is an option. An OCR vendor that starts working on the shift today, should easily be able to develop, tune, test and productize an LLM-based OCR pipeline w…
Earlier quoted context omitted.
Check again, Elon and his Doge team killed that.
No they didn’t, that claim is ridiculously easy to debunk but it has been going around because it fits the narrative.
In this case, the reason for the misinformation is do to the lack of communication from the DOGE entity regarding their actions. Mr. Musk wrote via Tweet that he had "deleted" the digital services agency "18F" that develops the IRS Free File program and also deleted their X account.
https://apnews.com/article/irs-direct-file-musk-18f-6a4dc35a...
If indeed he did cut the agency, it remains to be see how long the application will be operational.
This is using exactly the wrong tools at every stage of the OCR pipeline, and the cost is astronomical as a result. You don't use multimodal models to extract a wall of text from an image. They hallucinate constantly the second you get past perfect 100% high-fidelity images. You use an object detection model trained on documents to find the bounding boxes of each document section as _images_; each bounding box comes…