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

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

news.ycombinator.com

Post reply on HN
Print view View original

791–800 of 1001 posts

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

#791

Post by reedlaw »

juanpabloaj wrote: post #629

These past weeks I finally organized some ideas I'd been sitting on and wrote two posts: From Agentic Reasoning to Deterministic Scripts: on why AI agents shouldn't reason from scratch on every repeated task, and how execution history could compile into deterministic automations https://juanpabloaj.com/2026/03/08/from-agentic-reasoning-to... The silent filter: on cognitive erosion as a quieter, more probable civiliza…

Do you have examples of the task maturation cycle? I'm not sure how it would work for tasks like extracting structured data from images. It seems it could only work for tasks that can be scripted and wouldn't work well for tasks that need individual reasoning in every instance.

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

#793

Post by hephaes7us »

I'm making a "Podcast Search Engine", partially as an excuse to play with Elixir and Phoenix/LiveView.

It's basically just a frontend to a semantic search system, and is a tangent while I explore "knowledgebase" concepts.

I'm extremely interested in knowledgebases at the moment.

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

#794

Post by phasetransition »

liu3hao wrote: post #537

Hi HN, I am still working on Circuitscript, a language based on python to describe electronic schematics: https://circuitscript.net/ . A basic IDE (called the Bench) to try Circuitscript is available online: https://bench.circuitscript.net/ In the past month, as suggested by the previous user, I have added support for kicad schematic libraries. The kicad schematic libraries files are converted into circuitscript form…

Like an open source JITX

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

#795

Post by rilkeanheart »

I've been working on my attempt to build a dating app that isn't evil and actually helps. It feels like my graduate project after 46 first dates on my way to getting married this summer.

The basic idea is daters "teach" an algorithm what they like and then the algorithm uses the collective set of preferences to match everybody (or as many as possible) for single in-app "get to know you" chats. Everything is one-on-one to avoid overload and dead-end chats.

I now have working versions in the app stores and I'm currently testing in Seattle.

[1] geml.co [2] App Store - https://apps.apple.com/us/app/geml-dating/id6756629998 [3] Play Store - https://play.google.com/store/apps/details?id=com.geml.andro...

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

#796

Post by ksri »

I am working on a declarative CLI for google docs/sheets/slides etc. The general idea is a "pull" command that converts the proprietary document into a local files like tsv or xml. The agent (claude code) then simply edits these files in place and calls "push". The library then figures out the diff and applies only the diff, taking care to preserve formatting and comments.

The hypothesis is that llms are better off getting the "big picture" by reading local files. They can then spend tokens to edit the document as per the business needs rather than spending tokens to figure out how to edit the document.

Another aspect is the security model. Extrasuite assigns a permission-less service account per employee. The agent gets this service account to make API calls. This means the agent only gets access to documents explicitly shared with it, and any changes it makes show up in version history separate from the user's changes.

Early release can be found over here - https://github.com/think41/extrasuite.

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

#797

Post by KellyCriterion »

rilkeanheart wrote: post #795

I've been working on my attempt to build a dating app that isn't evil and actually helps. It feels like my graduate project after 46 first dates on my way to getting married this summer. The basic idea is daters "teach" an algorithm what they like and then the algorithm uses the collective set of preferences to match everybody (or as many as possible) for single in-app "get to know you" chats. Everything is one-on-on…

I have been in this field professionally and tried to do the same. May I ask:

a) how are you going to do the marketing?

b) according to my experience, all this social/viral stuff etc. does not work anymore today

c) former ideas like content & SEO -> is dead

d) nobody wants to talk today about anymore on being on a dating app?

e) And Sorry for being an Ass here: After I've lost a not-that-low-number of funds due to "following this idea" (just for prototyping/alpha & beta & final release), my recommendation is: Stop this immediately, it will save you years of your life! Im absolutely pro creating whatever app or service you may come along, but please please forget the dating market

P.S.: you will come back to this comment in 4 -5 years, latest :-)

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

#798

Post by spacemanspiff7 »

I vibe coded a workout app that lives in the browser and is totally free unlike all the variants in the app store.

I did this in response to my trainer blowing me off.

Been spending quite a bit of time squashing bugs but it's now relatively stable and functional.

Check it out here, https://www.curlbro.com

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

#799

Post by KellyCriterion »

BrunoBernardino wrote: post #485

My wife and I continue to work on Uruky, a EU-based Kagi alternative [1]. Since last month we got deals with a couple more search providers but we’re still waiting for EUSP/STAAN to provide us with an API key (we have progressed through a few more forms and signatures and legal stuff, though). We’ve continued to get some paid customers and have exited beta last week, given everyone seemed to be quite satisfied and th…

I wish you good luck and a very healthy stamina :-))

Search is _incredibly_ hard, there are reasons why there are no real Google competitors.

Post reply on HN