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

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

news.ycombinator.com

Post reply on HN
Print view View original

961–970 of 1001 posts

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

#961

Post by kthakore »

itake wrote: post #442
kthakore wrote: post #201

I’m building Hammer Labs ( https://hammer.ai ) to study when healthcare AI agents are wrong and when they should refuse to answer (judgement). It started after spending 15 years building AI for insurers, hospitals, data companies, and startups. Almost every system ended with "a human reviews the output". That person was usually a nurse, medical director, or certified coder. These are some of the hardest people to hir…

I was trying to learn more about your project. The comment above was digestiable for me as a non-healthcare person, but the website is really difficult for me to understand. The web design (and text?) really come off as ChatGPT written, which lowers my interest in spending time to understand it.

@itake, updated it https://hammer.ai/ is that clearer?

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

#962

Post by basetensucks »

I've been working on `ankix` (https://github.com/joshgummersall/ankix), a CLI tool to turn YouTube/podcast transcripts, Kindle highlights, and other text into "glossed" (read: contextually translated) Anki cards using a local `ollama` model.

I've also been working on `summond` (https://github.com/joshgummersall/summond), a developer/agent friendly way to interact with OSX Launch Control. It aims to support all relevant Launch Control triggers using a nice `toml` config format, dynamic environment control, logs, and more. I've found it super useful and it's dotfile friendly.

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

#963

Post by jamesyun »

andy_ppp wrote: post #861
jamesyun wrote: post #859

I'm building Orate, a free public speaking app: • Users are given a prompt and have 2 minutes to answer. • Speeches are reviewed by AI and other users. Speaking eloquently "off the dome" is an incredibly useful skill, improving all your interactions with other people. And like a muscle, you can train it with dedicated practice until it becomes effortless. It has been very fulfilling to listen to other people's speech…

You could “Pokémon Go” this and allow people to find performances they find interesting on a random street corner anywhere! Great idea!

Hmm interesting idea, although not sure if my users would want to share their location with strangers. It's more designed to be a thing you do at home or on a walk (my favorite) to keep your communication skills sharp.

Part of the beauty of the app is that it's pseudo-anonymous. Nobody knows it's you (unless they can recognize your voice). I think that helps relieve some of the pressure with public speaking.

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

#964

Post by Klsimek »

I’m building a service for capturing, viewing, and sharing 3D spatial data. It currently supports ARKit and Apple LiDAR, enabling users to perform room scans within seconds and allows real-time streaming of 3D video, all viewable on the web using WebRTC and WebGPU.

The plan is to enable any tracked camera to relocalize against the same coordinate frame and share spatially-anchored data with one another, enabling across-ecosystem interoperation of spatial computing systems.

For example, a human with an iPhone can scan their home and use that map to guide their domestic robot (clean _this_ room). Data from iOT sensors can be viewed in a 3D map in their real location. Or someone in an AR headset can view yesterday’s surveillance footage in the same room where the footage took place. Android and iPhone users can share the same AR experience, and a remote viewer can observe and guide them from a birds-eye view, all from their phone’s web browser.

My problem: I’m a software guy (former Apple ARKit/Vision Pro computer vision engineer) and I’m struggling to navigate the business side of things. I’m looking for a business-savvy cofounder to help find the market and then seek funding.

If it sounds interesting, reach out and I’ll share a demo!

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

#965

Post by zopf »

Options market-making. I trained a custom volatility model on historical data, built a passive delta hedge MM, render a synthetic underlying price from many market data sources, and a number of other interesting elements. It has been really fun to get back to my trading systems roots after 12 years as a startup CTO selling to enterprise clients and managing teams and managers. Now I just manage a bunch of Fable and Opus claude code sessions and a handful of high-performance servers. Opus makes a lot of ignorant mistakes and then explains them in great detail, but if I spend lots of time in Plan mode and then bash my head against the wall enough, we get there. Fable mostly gets it right and communicates effectively; what a relief! Still need to give Astra a try. I still feel ahead of the models on context, but am getting outpaced in many other ways. It's a very fun collaboration!

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

#966

Post by tniemi »

nacnud wrote: post #854
tniemi wrote: post #150

Me and my wife (then my girlfriend) have written "realistic" space sci-fi in Finnish for over 20 years. Now with AI we are finally able to translate our stories to English. The quality starts to be there. There are a lot of small languages in the world, and translation used to be extremely expensive. And there is never too much good space sci-fi. (We don't write space battles or wars. Our style is slower and bit more…

Have you published any of these stories online? I'd love to read some!

Things are kind of under construction... We would like to publish our stories in book-on-demand format.

This is one of our early translation tests. I publish it here for a while for you: https://media.nimbus.fi/tero/for_hackernews/sleeping_childre... Please don't expect it to stay there forever.

It has the same heroine that is in our debut book: https://fi.wikipedia.org/wiki/Nimbus_ja_t%C3%A4hdet Every short story has the same main characters visiting an another star and an another world.

Here's some of the local space that I generated from Gliese/Hipparcos dataset some 20 years ago. I'm trying to port our original LightWave starmaps to Blender: https://media.nimbus.fi/tero/nimbus/local_space.png

We should probably write a blog (blag) post about the hurdles of translating from a small (and not so well supported language) to English. Luckily my wife is way better in English than I am.

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

#968

Post by chamomeal »

jesse__ wrote: post #139

I've been working on a voxel game engine called Bonsai for ~10 years. Probably the most interesting thing about it at the moment is the editor. The world, and most things in it, are represented as collections of SDFs. More accurately, they're density fields, but, potato-tomato. Bonsai has undergone a large rewrite over the last couple years that's nearing completion. A world edit is defined as a bunch of SDF paramete…

The draw distance thing is insane. I would love to see some ridiculously scary-huge landscapes!!

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

#969

Post by mikodin »

Greetings friends! I have been joyfully working on a native iOS app called Sanctum. I really built this for myself and use it multiple times a day (https://apps.apple.com/us/app/sanctum-the-voice-journal/id67...)

Sanctum is a voice journal, think Obsidian but for voice notes. I am really honing in on data sovereignty, privacy, 1 click to record and self organization of notes / ideas.

While this isn't anything revolutionary, or technically difficult, I do think I've landed on a form factor and stack that is in my opinion not served by current products. So much so that I just simply had to build it myself. Sanctum was born out of an Obsidian plugin that I built and have been maintaining for about 2 years called Scribe and it's been a wonderful way to really hone in on a more full fledged agentic development process for a full stack experience.

The stack is simple

  - For transcription I am using AssemblyAI - they have solid terms, 24hr retention and no training

  - LLM inference is running inside a TEE using redpill.ai, it's slow af but as private as I could find.

  - For cloud backup I am using full E2E encryption with Backblaze for storage

  - Endpoints and the like are AWS lambdas, DynamoDB for billing storage, Supabase for auth
I (yes, fully me, not AI) have been doing a lot of writing on the process, we are flooded with these sorts of post on HN, but if anyone is interested in reading, check it out! https://www.builtinspace.xyz/blog/begin-with-ethos.

Anyway, something I am most definitely curious on is if people are recording their thoughts, what they are using (either a cobbled together solution or a product) and what value they feel they've been getting from it!

Post reply on HN