constantinum

Staying with Garmin just for amazingly long battery life… and instinct series has solar too

Vi or Vim

In 2018 there was a beautiful New Yorker article on Jeff Dean and Sanjay https://www.newyorker.com/magazine/2018/12/10/the-friendship...

We are using https://mfbt.ai/

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” ??

Deepseek and Qwen Chat

I think LLMWhisperer might help you here https://pg.llmwhisperer.unstract.com/

Posthog

reminds me of this article > https://unstract.com/blog/understanding-why-deterministic-ou...

MonicaHQ

Audiobookshelf

Ghost crm

Immich for photo hosting

Mattermost

Matomo

Vimeo’s editor’s pick is my go to place for getting/staying inspired…

All Pulitzer price winning non-fiction books — specifically investigative journalism - is always a great read

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

- 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

Selfish Gene, Thinking fast and slow, Pale blue dot

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/

Sentry's homepage has a toggle called "no-marketing mode" which when turned on removes all the marketing fluff.

Ken Thompson interviewed by Brian Kernighan at VCF East in 2019 > https://www.youtube.com/watch?v=EY6q5dv_B-o

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...

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/

I sort of use SuperWhisper, it is sort of good. https://superwhisper.com/

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

anyone looking for an ocr or text pre-processor that maintains the layout(tables, forms) try LLMWhisperer > https://pg.llmwhisperer.unstract.com/

Other players:

1. Trellis (YC W24) 2. Roe AI (YC W24) 3. Omni AI (YC W24) 4. Reductor (YC W24)

Other players(extended):

1. Unstract: Open-source ETL for documents (https://github.com/Zipstack/unstract) 2. Datalab: Makers of Surya/Marker 3. Unstructured.io

Mobile phones from the past 15 years. Film cameras. Vinyl records (you have to see the look on today's kids' faces when they hear music from playing records).

Photography, music, books, cooking

In a way only marketeers think hubspot does very good product marketing. (i’m a user of hubspot for 8 years or so)

Another common stack that is commonly use is Langchain + Pydantic https://unstract.com/blog/comparing-approaches-for-using-llm...

There is also Unstract open-source. Structured data extraction + ETL. https://github.com/Zipstack/unstract

Thanks for the tip.