News for hackers. Stuff that matters.

arvind_k

At Zipphy, I worked on solving similar problems in on-prem environments — building an OCR + NLP + CV pipeline to generate spatial layouts and classify documents at scale.

One persistent challenge was generalizing across “wild” PDFs, especially multi-page tables.

Your mention of agentic OCR correction and semantic chunking really caught my attention. I’m curious — how did you architect those to stay consistent across diverse layouts without relying on massive rule sets?

Ask HN: Looking for an AI Research Mentor

Hi HN,I’m a senior software developer with 20 years of experience in architecture, backend systems, and product development. Over the last few years, I’ve become deeply interested in AI and machine learning — not just building with existing tools, but understanding and contributing to AI research itself.I’m looking for a mentor (ideally a researcher, academic, or industry professional) who can...

( Read More... | no comments | on HN )
Thanks MIke will take a look at Lumen

Ask HN: What Changes When Adtech Moves from Keyword to Context-Based Targeting?

Adtech is seeing a major shift—from keyword-based targeting (search, bid, intent) to more context-driven approaches (content, behavior, semantics, attention signals). With increasing privacy regulations, deprecation of third-party cookies, and rise of LLMs, the ability to interpret context in real-time is becoming central to modern ad targeting.I'm curious:What are the key technological shifts...

( Read More... | 2 comments | on HN )
Re:Ask HN: Who is hiring? (March 2023) on Friday March 03, 2023 @08:35AM (#35009384)
d1vyank ,

can we connect offline and discuss

thanks Arvinf 94230096(five)(four)

Ask HN: Books/Articles around mind,Consciousness,perception and interrelation

As some one who is intellectually curious and has a longing to understand what how of the mind and its existence, can somebody point me to interesting materials on the net, I think i am just looking for a article or some thing which will produce a kind of eureka moment for me.If you have come across any article/book/channel which has produced that moment of clarity.Thanks

( Read More... | 3 comments | 2 points | on HN )
Re:Zipphy – Document Classifier /Splitter on Wednesday October 28, 2020 @07:11AM (#24917435)
yeah WIP
Re:Zipphy – Document Classifier /Splitter on Wednesday October 28, 2020 @07:11AM (#24917434)
thanks Ethan will try and embed your feedback
Re:Zipphy – Document Classifier /Splitter on Monday October 19, 2020 @01:21AM (#24823523)
Simple document modelling and classification platform.
Re:Ask HN: What would you want in an ideal web browser? on Monday August 17, 2015 @04:07AM (#10071774)
no ads in any form
Re:Ask HN: Recommended JavaScript books? on Wednesday January 09, 2013 @05:56PM (#5034085)
Java script the good parts is worth a read

Ask HN : Product Development outsourcing

we are group of seniors(kick ass) developers who in the past have built SAAS, PAAS and Analytics products(can give refernces in private), so was wondering if anybody is interested in getting product development donewhat is best place to look @ on the web, we just started dont want to go through FreeLance sites since we want to build long term relation and teams for the company and not look for...

( Read More... | no comments | on HN )