Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ingesting PDFs and why Gemini 2.0 changes everything

sergey.fyi

Post reply on HN
Print view View original

421–430 of 456 posts

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#421

Post by montecruiseto »

kbyatnal wrote: post #198
lazypenguin wrote: post #27

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…

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…

So why should I still use Extend instead of Gemini?

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#422

Post by cpursley »

fragmede wrote: post #382
cpursley wrote: post #350

Earlier quoted context omitted.

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.

If I'm an autobody shop or some other well-served niche, how unhappy with them do I have to be to decide to find a replacement, either a competitor of theirs that used an LLM, or bring it in house and go off and find a developer to LLM-acceleratedly make me a better shopmonkey? And there are the integrations. I don't own a low hanging fruit SaaS company, but it seems very sticky, and since the established company alr…

Integrations is part of the data moat I mentioned.

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#423

Post by Dylan16807 »

TeMPOraL wrote: post #420
Dylan16807 wrote: post #419

Earlier quoted context omitted.

> could affect how threads are allocated to CPU cores and order in which they finish I'm very confused by how you're interpreting the word "each" here. > Being able to assume commutativity gives you a lot of flexibility in how you parallelize it, and allows you to minimize overhead (both in throughput and memory requirements). Splitting up a single neuron seems like something that would only increase overhead. Can yo…

I feel like you're imagining a toy network with couple dozen neurons in few layers, done on a CPU. But consider a more typical case of dozens of layers with hundreds (or thousands) of neurons each. That's some thousand numbers to reduce per each neuron. Then, remember that GPUs are built around thousands of tiny parallel processors, each able to process a bunch (e.g. 16) parallel threads, but then the threads have to…

I'm not imagining toy sizes. Quite the opposite. I'm saying that layers are so big that splitting per neuron already gives you a ton of individual calculations to schedule and that's plenty to get full usage out of the hardware.

You can do very wide calculations on a single neuron if you want; throwing an entire SM (64 or 128 CUDA cores) at a single neuron is trivial to do in a deterministic way. And if you have a calculation so big you benefit from splitting it across SMs, doing a deterministic sum at the end will use an unmeasurably small fraction of your runtime.

And I'll remind you that I wasn't even talking about determinism across architectures, just within an architecture, so go ahead and optimize your memory layouts and block sizes to your exact card.

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#425

Post by uri_merhav »

Gemini Flash 2.0 is impressive but it hardly captures all of the information in the PDF. It's great for getting vibes from the document or finding overall information in it. If you ask it to e.g. enumerate every line item from multiple tables in a long PDF it still falls flat (dropping some line items or entire sections etc). DocuPanda and to a lesser extent Unstrucutred handle this.

Re: Ingesting PDFs and why Gemini 2.0 changes everything

#427

Post by ethbr1 »

sitkack wrote: post #411
collingreen wrote: post #402

Earlier quoted context omitted.

I assume this is a slap intended to imply that ai actually IS a silver bullet answer to the parent's described problem and in just 18 months they will look back and realize how wrong they are. Is that what you mean and, if so, is there anything in particular you've seen that leads you to see these problems being solved well or on the 18 month timeline? That sounds interesting to look at to me and I'd love to know mor…

It isn't a silver bullet in that it can just "make software" but it is changing the entire dynamic. You can't do point sampling to figure out where things are going. We have to look at the slope. People see a paper come out, look at the results and say, "this fails for x, y and z. doesn't work", that is now how scientific research works. This is why two minute papers has the tag line, "hold on to your papers ... two…

That's not why more experienced people are doubting you.

They're doubting you because the non-digital portions of processes change at people/org speed.

Which is to say that changing a core business process is a year political consensus, rearchitecture, and change management effort, because you also have to coordinate all the cascading and interfacing changes.

Post reply on HN