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

How? The user (skier!) uploads a short ski clip to Poser, lets Poser analyze, and then gets their results.

For now, you get video outputs: head-tracking and skeleton overlay. I’ve built a a lot of extra stuff (animated 3D body, turn-detection, balance-, steering-, pressure-, and edging-metrics, etc.), I’m just not sure how to package it all to be useful. So as of this post, videos are what’s available.

I’m using Meta AI’s SAM3 Tracking and SAM3D Body for skier tracking and pose estimation. The heavy lifting happens in Runpod.

I’m a software developer, Bachelor and Masters in Applied Phyiscs, and a ski instructor in the Austrian and Danish ski schools. So I thought to combine all three passions in Poser!

1) https://www.tirreno.com

2) https://github.com/tirrenotechnologies/tirreno

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

https://getnile.ai

Our thesis is that a lot of Data Engineering work is non-differentiated across companies. Rather than focusing on repetitive tasks (i.e. creating a new table), people want to spend more time on higher level work like analysis. We’ve abstracted away a lot of the tedious parts of DE work so that you can focus on the critical needle moving tasks for your business.

We have a version that runs locally on your computer that is completely free. Would love to get thoughts and feedback from this community!