Live data from Hacker News

Ask HN: What Are You Working On? (April 2026)

news.ycombinator.com

981–990 of 1001 posts

Re: Ask HN: What Are You Working On? (April 2026)

#985
https://github.com/johnwatson11218/LatentTopicExplorer/

This tool allows you to read in a collection of pdf files and it will use AI to create clusters of documents based on semantic content. Pdfplumber -> postgresql -> 1 doc 2 many pages -> pages embedded using sentence_transformers -> 384 reduced to 2d for plotting using UMAP -> custers identified using HDBScan -> labels identifed using class based tf-idf implemented inside of postgresql using stored procedures. Once the files are read in the system is more stable and reliable. My personal document collection in about 1200 files and the ingestion takes 12 to 24 hours on my various laptops. Once that is done the website is very fast.

Re: Ask HN: What Are You Working On? (April 2026)

#986
www.bundleup.io - I’ve been working on a way to stop rewriting OAuth flows for every API. Integrations start simple but turn into a mess once you deal with refresh tokens, retries, and edge cases. Still early, but it’s been useful for my own projects so far.

Re: Ask HN: What Are You Working On? (April 2026)

#990
I am building https://www.simplyhra.com which helps companies reimburse health spendings for employees. We wanted not just a platform who help people find a health insurance and pay for that, so we started building an AI enabled concierge service, which helps you book for care, messages with your doctor in different EHR platforms on behalf of you and moves your health records from EHR to your LLM context. Coming soon!
Post reply on HN