Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: What are you working on? (May 2026)

news.ycombinator.com

Post reply on HN
Print view View original

851–860 of 1001 posts

Re: Ask HN: What are you working on? (May 2026)

#855

Post by f_k »

https://citellm.com

Building CiteLLM, an API that extracts structured data from PDFs and returns exact source locations for every field.

There's also a widget so you can add click-to-verify to your own app in a few lines of code.

Click any value, jump straight to the highlighted source in the PDF.

Demo: https://citellm.com/demo

Re: Ask HN: What are you working on? (May 2026)

#856

Post by anupmm »

jstrebel wrote: post #582

I am trying to build a simulation that lets a simulated organism come up with its own small language, purely learned from sensory input: https://github.com/JoergStrebel/VirtualZoo/blob/main/compute... I would like to implement the ideas put forward by Stevan Harnad in his symbol grounding problem paper (Harnad, 1990).

Hi - This sounds interesting and is an area that has fascinated me for quite some time. I think it is possible to build an agent whose intelligence emerges from preserving viability, learning which perceptions/actions are worth their metabolic cost, and grounding concepts in sensorimotor experience. I have been inspired by the ideas of Karl Friston, Anil Seth and the like. Following!

Re: Ask HN: What are you working on? (May 2026)

#857

Post by tedd4u »

binsquare wrote: post #539

I'm working on building a virtual machine that has the fast boot and portability of containers. It's called a smol machine free and oss, https://github.com/smol-machines/smolvm

This is cool - thanks for sharing. I'd love to see a column for LXC in the comparison table (in the README).

Re: Ask HN: What are you working on? (May 2026)

#858

Post by yeag123 »

I've been working on this for about a year and a half, and decided to finally open source it.

I wanted an intelligent document processing SaaS (Document AI, Form Recognizer, the various PDF-to-JSON tools) that you could run on your own hardware.

The interesting bits:

- Three-tier extraction: PyMuPDF for digital PDFs (~50ms), Docling layout-only for scanned-but-readable, Docling+OCR for the rough stuff. Auto-fallback based on extracted character count. - Smart templates use vector similarity (Qdrant) to classify docs, then LLM extraction for fields — no regex, so layout drift doesn't break templates. - Local Ollama or Azure OpenAI, switchable per-user.

Built on top of Cole Medin's local-ai-packaged. Apache 2.0.

https://github.com/nickyeager/fetchtext

Re: Ask HN: What are you working on? (May 2026)

#859

Post by korbonits »

nicoinstrument wrote: post #21

I'm learning about inference by running vLLM on a k8s cluster (EKS), building a gateway to keep a Most recent ha-ha moment: I kept wondering if it was normal that my cluster was only able to process 4 requests per second per vLLM engine (just seemed really low to me). I realized a better metric is in-flight requests... Each engine is processing 70 requests at any given time, streaming tokens for over 30s. Code: https…

Have you considered using vLLM on top of Ray Serve (on EKS with KubeRay)? KubeRay makes Ray cluster-aware and there could be some optimizations you could make e.g. keeping that GPU fully utilized all the time :)

Re: Ask HN: What are you working on? (May 2026)

#860

Post by neurodiv_dennis »

madman_dev wrote: post #611

I'm constantly working on https://only-eu.eu/en A directory of European software and general alternatives to popular products. Think cloud storage, email, VPN, browsers, smartphones, bikes,... About 175 products across 30+ categories right now. Next categories will be: personal health, commercial e-mail and newsletter management. If you have a product that's missing here, please feel free to suggest it via the sugges…

Sounds pretty cool!

I've been taking a look at it and browsed through the categories. Is it also for apps? Now that I'm writing this - as I saw WhatsApp as an example with 5 alternatives listed - probably yes. So let me reframe the question: Does it have to be an alternative to some other existing thingy or are you also willing to list genuine apps?

Asking for a friend ;-)

Post reply on HN