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

Ask HN: What are you working on? (February 2025)

news.ycombinator.com

Post reply on HN
Print view View original

81–90 of 922 posts

Re: Ask HN: What are you working on? (February 2025)

#81

Post by mavamaarten »

I live next to a school, so there's a low speed limit (30 km/h). Still, people drive like race drivers and the city hasn't ever responded to the residents' hopes of introducing a speed camera.

I wanted to have some data on how many people speed, the max speed recorded, that sort of thing. Things the city should be doing after many complaints of dangerous driving and people being almost killed on zebra crossings.

I have a doorbell camera, and by analysing the footage using OpenCV and some code, I can track how fast people drive if you see how fast they move between two known points.

Average speed: 46 km/h :(

Re: Ask HN: What are you working on? (February 2025)

#82

Post by renegat0x0 »

I am maintaining the internet on the github. Take a look.

[0] https://github.com/rumca-js/Internet-Places-Database

I use it for various projects, like simple search

[1] https://rumca-js.github.io/search?page=1&search=emulation

[2] https://rumca-js.github.io/search?page=1&search=amiga

Re: Ask HN: What are you working on? (February 2025)

#83

Post by Ccecil »

Finishing the feeder "hack" to my pick and place machine [1] so that I can begin full retail production in house of the V2 Smoothieboard CNC controller [2].

As well as finishing shipping the remaining boards to the kickstarter backers (many years late, but significantly better).

Been a long struggle overall...learned a lifetime's worth during the last couple years. Every single day has been spent doing something new it seems. Looking forward to what the next broken machine will teach me :)

[1] https://youtu.be/Vk53VsXkh9o?si=SU45-DkkjwZi6orp [2] https://github.com/Smoothieware/Smoothieboard2 https://github.com/Smoothieware/SmoothieV2

Re: Ask HN: What are you working on? (February 2025)

#84

Post by j-rom »

Trying to scratch my own itch by creating (yet another) todo list site. It's more for me than anyone else. I typically use a simple text file to track my tasks in a day but I wanted something just a little bit more. Still minimal but maybe 1 - 2 steps above editing a file.

Donezo: https://donezo.pages.dev/

Re: Ask HN: What are you working on? (February 2025)

#86

Post by Imustaskforhelp »

josters wrote: post #71

Was looking for an iOS app to always see my age in days on the lock screen. Didn‘t find one, so I first created a shortcut which would change my lock screen background image each night and overlay the number of days on it. This didn’t feel integrated enough and could fail if the phone was off, so I started looking into Swift and created my first app [1] with added features like contact import and notifications for ot…

nice job , I think I can do something like that on with my linux desktop. Great idea , it can give a sense of how many days how many hours I have lived on this earth and maybe even by a average time , show how much time is left (yes it won't be predictable , but I also don't want to procastinate thinking there is a tomorrow , I think I like steve jobs quote in the manner that he said live your life as if its the last hour or something like that.

Re: Ask HN: What are you working on? (February 2025)

#88

Post by brainless »

soulofmischief wrote: post #64
brainless wrote: post #40

I have been working full-time for about 15 months on a product to store real-world entity-relations in a graph (using AI/ML for extraction). The idea is to extract entities and relations deterministically from text (using AI/ML for clues about type and position of entities in text). It is very much a work in progress with lots of commented out code which are just experiments. https://github.com/pixlie/PixlieAI

Nice project! I built something extremely similar with a friend in 2022! Back when we only had the GPT-3 API. I built an ontological graph and relation extractor, mental model analysis engine, bunch of stuff, on top of an Elastic DB being filled with live incoming ephemeral data across the web, including messages, comments, posts, articles and more. I would really love for you to reach out via the email in my bio so…

This sounds lovely. This product has not reached to the point where ontology matters, that is still far away.

I am just going for the low hanging fruits - very basic stuff like location, person, event, activity, date (a few more things) and relations between them. One of the limitations is that I want to do deterministic extraction with suggestions from AI/ML, so there is much code to be written. I will email you, thanks a lot!

Re: Ask HN: What are you working on? (February 2025)

#89

Post by kilowatt »

maxbond wrote: post #58
kilowatt wrote: post #51

An LLM assistant app for engaging with your journal. Insights, prompts (for humans), research leads, etc.

I'd be curious to hear more. I presume you're using some kind of semantic search? Any other kinds of semantic technology? What kinds of insights into your journaling has it offered you/users?

The work thus far has mostly been on a seamless mobile UI, & to make engaging with the LLM like less of a chat and more like browsing an interesting dynamic wiki about your own life. But also, yes, a highlight for me re: having your journal in context can be to search and find commonalities, patterns.

I would say the insights frontier models have given me, at a high level, match some of those offered by professionals in a theraputic context--which is one reason I'd be curious to make an affordable/accessible app. Although I tread lightly into depersonalizing such a human area with techno utopian naivete...

Re: Ask HN: What are you working on? (February 2025)

#90

Post by muxneo »

My family uses multiple messenger apps - WhatsApp, Slack, Discord etc. I get so many messages on these everyday. I am also member of multiple WhatsApp groups and slack channels. Needless to say, I miss out on a lot (actually every) important message in groups and channels and sometimes DMs. I am working on ML solution to summarize the messages and info in these messengers for people whenever they access my service. The idea is to reduce the amount of info from 100:1 and give extremely succinct data without losing any important info.

WOULD YOU BE INTERESTED?

Post reply on HN