Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by dgan on Tuesday June 03, 2025 @06:04AM
(#44168249)
Tried Claude yesterday to help me extract rows from a financial statement PDf. Let's automate boring stuff !!
After multiple failures , I did it myself
[ Parent
| on HN ]
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by terhechte on Tuesday June 03, 2025 @06:51AM
(#44168531)
I sat down at a Piano yesterday and tried to play a beautiful song even though I never really used a piano before. Sounded horrible, must be the pianos fault.
One reason to use LLMs is to understand when and how to use them properly. They're like an instrument you have to learn. Once you do that, they're like a bicycle for your mind.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by dgan on Tuesday June 03, 2025 @06:54AM
(#44168554)
except the piano's seller advertised that i don't need to know how to play "just ask it, it will play!"
Here ya go, fixed your analogy
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by lapcat on Tuesday June 03, 2025 @06:55AM
(#44168563)
LLMs can't disappoint. They can only be disappointed.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by 112233 on Tuesday June 03, 2025 @09:02AM
(#44169563)
Which model have you picked to learn and keep using? Because each new model means learning new instrument.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by xela79 on Tuesday June 03, 2025 @09:16AM
(#44169753)
ah yes, all those LLM models have such unique and different system prompts, impossible to re-use your knowledge from model A for model B...
or wait... https://github.com/elder-plinius/CL4R1T4S nah, they are very much the same when it comes to prompting
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by dingnuts on Tuesday June 03, 2025 @09:52AM
(#44170171)
system prompts aren't actually part of the model at all; obvious you don't know what you're talking about.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by xela79 on Wednesday June 04, 2025 @03:26AM
(#44178061)
wauw. your point was that you needed to relearn "all the prompting" when a model changes. which is not the case. but hey. at least you know what you're talking about.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by 112233 on Wednesday June 04, 2025 @04:00AM
(#44178282)
It was actually mine point, not theirs. But yes, you do actually need to lelearn "all the prompting" when switching models. Would gladly see any tests you have made or any published studies that show it is not the case anymore with newer models!
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by benwad on Tuesday June 03, 2025 @09:24AM
(#44169836)
If you buy a machine to play the piano for you, you won't learn how to play the piano. You'll just become really good at using that machine.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by kaptainscarlet on Tuesday June 03, 2025 @06:43AM
(#44168472)
LLMs are like a child with undiagnosed ADD, it is a constant roller coaster with peaks of amazement and and equally dips of disappointment.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by jrs235 on Tuesday June 03, 2025 @07:23AM
(#44168773)
Currently my biggest gripe is asking AI to make one modification to file, it then decides to do 4 other "extra" changes I didn't ask for. AI please stay focused!
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by Etheryte on Tuesday June 03, 2025 @06:07AM
(#44168275)
As with any other tool, half the art of using LLMs productively is the ability to recognize when they're a good fit and when they're not. So long as AGI doesn't come around, there will always be cases where they fall on their face and as far as I'm concerned, we're pretty far from AGI.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by robertlagrant on Tuesday June 03, 2025 @06:07AM
(#44168267)
Think how much energy would be saved if you could embed a sqlite database in a pdf with the data in it.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by graemep on Tuesday June 03, 2025 @06:27AM
(#44168387)
There are formats that are structured - XBRL.
If you want it to be human readable you can use iXBRL which is embedded in HTML.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by submeta on Tuesday June 03, 2025 @07:00AM
(#44168606)
Try Mistral OCR. They trained their model to extract data from PDF. Used it to convert pdf forms to json schema. Worked excellently.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by dgan on Tuesday June 03, 2025 @08:45AM
(#44169385)
i will give it a try tonight & report back!
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by dgan on Friday June 06, 2025 @04:07PM
(#44204502)
Okey so Mistral is definitely better at reading PDFs and extracting usefull information
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by benterix on Tuesday June 03, 2025 @07:32AM
(#44168849)
Claude is not good for thus, try Mistral OCR. I'm using it on a daily basis on English and non-English texts and it works very well.
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by Flemlo on Tuesday June 03, 2025 @06:57AM
(#44168578)
Did you try Claude to just extract it or to write a python script to do so?
Re:Stop Over-Thinking AI Subscriptions – Peter Steinberger
by keepsweet on Tuesday June 03, 2025 @10:22AM
(#44170459)
Most people don't realize that LLMs by design were not made for document processing, data extraction etc. For that, you would have to use a dedicated tool like Klippa DocHorizon, which built its own AI OCR from scratch. It also provides an API that you can use to send your documents and receive formatted data. It's less popular than, say, Textract or Tesseract, but it's far more accurate, especially if you're dealing with sensitive data that you wouldn't want an LLM to hallucinate.