HackerTrans
TopNewTrendsCommentsPastAskShowJobs

constantinum

no profile record

Submissions

Simplicity, Agency, and Mastery

hgrsd.nl
3 points·by constantinum·16 วันที่ผ่านมา·0 comments

Balsamiq Turns 18

e.customeriomail.com
2 points·by constantinum·22 วันที่ผ่านมา·0 comments

NetNewsWire Status

inessential.com
4 points·by constantinum·25 วันที่ผ่านมา·0 comments

Raspberry Pi profit surges as AI boom lifts demand

ft.com
30 points·by constantinum·3 เดือนที่ผ่านมา·11 comments

A Couple Million Lines of Haskell: Production Engineering at Mercury

blog.haskell.org
5 points·by constantinum·3 เดือนที่ผ่านมา·0 comments

Visitran: Agentic Pythonic data transformation platform(AGPL)

github.com
5 points·by constantinum·4 เดือนที่ผ่านมา·0 comments

A practical guide to observing the night sky for real skies and real equipment

stargazingbuddy.com
121 points·by constantinum·5 เดือนที่ผ่านมา·21 comments

FinePDFs: Liberating 3T of the finest tokens from PDFs

huggingface.co
2 points·by constantinum·6 เดือนที่ผ่านมา·0 comments

Sentry – No Marketing Mode

sentry.io
1 points·by constantinum·8 เดือนที่ผ่านมา·1 comments

Reducto Raises $108M to Shape the Future of AI Document Intelligence

reducto.ai
2 points·by constantinum·9 เดือนที่ผ่านมา·0 comments

Iconfinder will permanently close on November 15, 2025

support.freepik.com
4 points·by constantinum·9 เดือนที่ผ่านมา·0 comments

comments

constantinum
·4 เดือนที่ผ่านมา·discuss
We are using https://mfbt.ai/
constantinum
·4 เดือนที่ผ่านมา·discuss
I also want to try Qwen 3.5 plus. I have a doubt, I see almost same pricing for both Qwen and Claude code(the difference being the highest pro plan looks cheaper), and not for the lower plans. Am I missing something, when you say “cheaper” ??
constantinum
·4 เดือนที่ผ่านมา·discuss
Deepseek and Qwen Chat
constantinum
·4 เดือนที่ผ่านมา·discuss
I think LLMWhisperer might help you here https://pg.llmwhisperer.unstract.com/
constantinum
·5 เดือนที่ผ่านมา·discuss
Posthog
constantinum
·5 เดือนที่ผ่านมา·discuss
reminds me of this article > https://unstract.com/blog/understanding-why-deterministic-ou...
constantinum
·5 เดือนที่ผ่านมา·discuss
MonicaHQ

Audiobookshelf

Ghost crm

Immich for photo hosting

Mattermost

Matomo
constantinum
·6 เดือนที่ผ่านมา·discuss
Vimeo’s editor’s pick is my go to place for getting/staying inspired…
constantinum
·6 เดือนที่ผ่านมา·discuss
All Pulitzer price winning non-fiction books — specifically investigative journalism - is always a great read
constantinum
·6 เดือนที่ผ่านมา·discuss
What matters most is how well OCR and structured data extraction tools handle documents with high variation at production scale. In real workflows like accounting, every invoice, purchase order, or contract can look different. The extraction system must still work reliably across these variations with minimal ongoing tweaks.

Equally important is how easily you can build a human-in-the-loop review layer on top of the tool. This is needed not only to improve accuracy, but also for compliance—especially in regulated industries like insurance.

Other tools in this space:

LLMWhisperer/Unstract(AGPL)

Reducto

Extend Ai

LLamaparse

Docling
constantinum
·7 เดือนที่ผ่านมา·discuss
- Permutation City — Greg Egan

- She Said — Jodi Kantor & Megan Twohey

- Conclave — Robert Harris

- First You Write a Sentence — Joe Moran

- Eleanor Oliphant is Completely Fine — Gail Honeyman

- The Master and Margarita — Mikhail Bulgakov

More books here -> https://pastebin.com/XVeacpHM
constantinum
·7 เดือนที่ผ่านมา·discuss
Selfish Gene, Thinking fast and slow, Pale blue dot
constantinum
·7 เดือนที่ผ่านมา·discuss
At instances where data accuracy is of paramount importance, i think a hybrid route of non-llm ocr for data parsing and LLMs for structured data extraction is the safe passage to tread on. Seen better results for LLMWhisperer(OCR)[1] and Latest Gemini.

[1] - https://pg.llmwhisperer.unstract.com/
constantinum
·8 เดือนที่ผ่านมา·discuss
Sentry's homepage has a toggle called "no-marketing mode" which when turned on removes all the marketing fluff.
constantinum
·9 เดือนที่ผ่านมา·discuss
Ken Thompson interviewed by Brian Kernighan at VCF East in 2019 > https://www.youtube.com/watch?v=EY6q5dv_B-o
constantinum
·9 เดือนที่ผ่านมา·discuss
Why PDF parsing is Hell[1]:

Fixed layout and lack of semantic structure in PDFs.

Non-linear text flow due to columns, sidebars, or images.

Position-based text without contextual or relational markers.

Absence of standard structure tags (like in HTML).

Scanned or image-based PDFs requiring OCR.

Preprocessing needs for scanned PDFs (noise, rotation, skew).

Extracting tables from unstructured or visually complex layouts.

Multi-column and fancy layouts breaking semantic text order.

Background images and watermarks interfering with text extraction.

Handwritten text recognition challenges.

[1] https://unstract.com/blog/pdf-hell-and-practical-rag-applica...
constantinum
·9 เดือนที่ผ่านมา·discuss
I use LLMWhisperer[1] for OCR'ing old magazine ads. It preserves the layout and context. Example > https://postimg.cc/ts3vT7kG

https://pg.llmwhisperer.unstract.com/
constantinum
·9 เดือนที่ผ่านมา·discuss
I sort of use SuperWhisper, it is sort of good. https://superwhisper.com/
constantinum
·9 เดือนที่ผ่านมา·discuss
1. Bill Cunningham New York

2. General Magic(2018)

3. The Armstrong Lie

4. Icarus (2017 film)

5. Man on Wire

6. Baraka & Samsara

7. BBC Planet Earth

8. Finding Vivian Maier
constantinum
·9 เดือนที่ผ่านมา·discuss
anyone looking for an ocr or text pre-processor that maintains the layout(tables, forms) try LLMWhisperer > https://pg.llmwhisperer.unstract.com/