I am working on creating a GAN for predicting the next few heartbeats given an ECG signal and hoping that the administration does not defund this project because I am being paid by a university project funded by the NIH.
Ask HN: What are you working on? (March 2025)
171–180 of 1001 posts
Re: Ask HN: What are you working on? (March 2025)
#172I just submitted a TinyML paper last night, focusing on creating a reproducible pipeline for model selection, compression, and deployment on constrained devices. I hope it gets accepted!
Re: Ask HN: What are you working on? (March 2025)
#173Working on v2 of our n+1-proof/reactive TypeScript ORM, Joist (https://joist-orm.io/), that moves to using the new-ish postgres.js driver (instead of knex/node-pg), so that we can leverage postgres.js's statement pipelining within transactions.
I'm anticipating a really sweet perf increase (as shown by some proof-of-concepts), but now that everything is actually working on the v2 branch, I'm putting together benchmarks that show the benefit in practice.
Love to have anyone poke around/ask questions/hang out on discord.
Re: Ask HN: What are you working on? (March 2025)
#174I have been filling my brain.
A long time ago I played around with neural net stuff and had some fun making tiny little things. To give an idea of time frame, this was before people were using ReLU.
Going back to it after the recent advances was incredible seeing how much has happened. So many times I'd see something and wondered how I could have missed it the first time only to realise it hadn't been invented yet when I did things last time.
It feels like there is a much higher focus on statistical mathematics now in a way that it permeates everything. That in itself requires a whole lot of new learning to get to grips with, but I also feel like there might be some value in looking at a lot of these things from a different perspective. I think I tend to look at things from a more geometric point of view.
In that vein I have been looking at some transformers using unit n-sphere embeddings with V values as geodesics, just to see what happens.
As I learn new things, I keep finding fun new ideas to muck around with, I'm just an amateur, so I'm not really restricted by areas I look at. Today I'm wondering about whether Wasserstein distance could be quickly approximated by a learnable method (especially if the inputs had access to parts of the ml components that generated the things being Wasserstein compared).
I'm almost certainly treading ground well explored by others, but my way of learning seems to be to rapidly jump between many different things picking up a small understanding of each as I go until I just seem to know things that I didn't before. Focusing on a topic and pushing in that direction never seemed to work for me so much. This is probably why I am an amateur :-)
Re: Ask HN: What are you working on? (March 2025)
#175I developed multi-ssh, it's a command-line utility designed to simplify the management of simultaneous SSH connections to multiple remote servers. It leverages tmux to create organized sessions, allowing you to interact with servers in separate panes within a single window or in individual windows per server. Features include synchronized input across panes, executing commands on all servers, copying files using rsync, and customizable configurations via a config file.
Re: Ask HN: What are you working on? (March 2025)
#176I am working on A tool to help governments better serve their citizens by using AI to automate complex multi-party workflows.
Re: Ask HN: What are you working on? (March 2025)
#177I just launched the beta for Table Slayer. It lets you build animated maps for in person RPG games (DnD, Pathfinder...etc) where you have a digital table top. It's built on Svelte + Turso + websockets.
The video here best shows it off. The source is available and free to use for non-compete, personal use.
https://bsky.app/profile/davesnider.com/post/3lkvum6xtjs2e
Mostly a labor of love. I don't expect there to be a super large audience for this one, it was just something I needed myself.
Re: Ask HN: What are you working on? (March 2025)
#178Working on my personal blog (https://bryanhogan.com/) recently. Updated some older posts such as the one on creating a gaming backlog (or similar) within Obsidian.
Also making a customizable self-tracking app that can be used as a habit tracker, health log, journal or similar. Goal is to make daily manual entries efficient and worthwhile. It will be local first and without an annoying subscription.
If anyone is personally interested in it or knows someone who could profit from something like this (e.g. because of their health condition) contact me please. Looking for testers and feedback to make it useful for people of various backgrounds and health conditions.
Re: Ask HN: What are you working on? (March 2025)
#179https://aponlink.com/ I built a no-AI, human-only social network focused on ONLY one thing - keeping people connected. I'd stepped away from mainstream social media last year due to the overwhelming negativity, privacy violation, etc. Then around early this year, I started to feel I was missing updates from people who actually matter in my life. Instead of going back to traditional platforms, I decided to create a si…
Trying to sign up, got this error: Error Firebase: Error (auth/network-request-failed).
Thanks for trying it out!
That particular error usually happens due to a temporary network issue or if third-party cookies are blocked. Could you try refreshing or using a different browser?
I’ll also check on my end to make sure everything is running smoothly. Appreciate the heads-up!
Re: Ask HN: What are you working on? (March 2025)
#180A tool for learning German via reading. The main feature is click a word to see its dictionary entry (not always easy with so many declensions). Flashcard creation from the dictionary entry. Real human spoken audio from Wiktionary.
Will be working on some LLM features soon (explain "X" in the sentence "Y" prompt). It'd be nice to get a word frequency ranking dataset integrated, so I don't waste time learning rare words.