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

561–570 of 922 posts

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

#561

Post by grayhatter »

xerox13ster wrote: post #458
apsurd wrote: post #132

Earlier quoted context omitted.

"being a grand dad" is his answer. and he colored it. it's not that deep so as to upset you. darklake just practicing his creative writing.

Colored it a corporate beige. Who the heck is so brain broken as to talk about their grandchild as a startup project and their family as a frigging team. I have to almost need to see this as AI in order to maintain sanity because there’s no way an actual human being talked about a child—their human grandchild like he was a product.

you're telling on yourself, highlighting that you're so humorless that you couldn't tell it was an intentional parody of corporate double speak, contrasting one of the most human experiences with one of the least human. It's ironic that you tried to call him brain broken lol

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

#563

Post by AJRF »

donohoe wrote: post #463
AJRF wrote: post #127

I recently made a little tool for people interested in running local LLMs to figure out if their hardware is able to run an LLM in GPU memory. https://canirunthisllm.com/

Feature Request: Looks like the React JS is 1.1MB out of the ~ 1.6MB the site takes to load all other assets. Do you really need React for this? That aside, I think this is really cool and very helpful. Thank you.

I am using Streamlit, and it is the thing that is adding React.

I appreciate that it's a heavy site, but just being honest with you - it doesn't seem worth the time optimising this by moving to another lighter framework at this stage of the project.

Sorry!

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

#564

Post by gloosx »

I'm exploring the world of Tauri cross-platform desktop apps in my free time now.

For the first project using this technology I decided to go for a simple media converter app. I have a 64MB sampler so I have to convert a lot of samples from lossless formats to mp3, there are two options I know: any random online tool from the google page 1 or ffmpeg cli. The former almost physically hurts, because I have to upload my files to some server which does the same ffmpeg instruction and then get them bytes back, that's a heck of an overhead!

ffmpeg-cli and some knee-made bash scripts is what I have been using for a long time. I love my console, and I spend 90% of the time inside, but then it comes to ffmpeg, it instantly feels tedious to use it. Finally I decided to make yet another GUI wrapper:

https://github.com/ilya-lopukhin/conversimp

The idea is to drag the files in, or select them via dialog, then run an ffmpeg conversion template with each file as input in a separate thread (need to limit theese btw). I decided to go fully open-source, and maybe promote it's usage over the online converter ad-farms which are really abundant. When I decided to publish this, I instantly understood it's going to be a tons of extra work, but in the end I want it to look nice and do it's job flawlessy, and at the moment it's a weekend or two from release.

Let me know what you think ;)

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

#565

Post by dv35z »

(1) 3D wood-craft! - I recently got a CNC router (it's a drill on a motorized arm, that can carve 3D shapes out of wood), and I've been challenging myself to build operate it completely from an open-source stack.

- Computer: Used Dell Optiplex, bought on the streets of Medellin Colombia

- Operating system: Debian Linux / XFCE

- 2D design: Inkscape

- 3D design: Kiri:Moto (https://grid.space/kiri/), soon FreeCAD

- CNC controller: Universal G-Code Sender (UGS) --> GRBL

I am passionate about "maker-space entrepreneurship" (it's the dream job), so I'm meeting potential clients in my city to understand their ambitions and challenges, so we can work together to make useful prototypes to solve them.

Useful forums:

- https://forum.makerforums.info/ - This is my "new Hackernews"

(2) Affirmator - I'm building a system where you provide your goals as affirmations (example: "I feel healthy, fit and strong", "Today's the day to make it happen"). The system then uses Text-to-speech to generate voice audio files. Next Affirmator uses `mpv` (media player - similar to VLC) and `cron` to automatically shuffle-play these affirmations every day in the morning & evening. I recently used Python and FFMPEG to add "vocalization pauses" at the end of the affirmation audio, so that you have time to say the affirmation out loud.

Some of the driver & inspiration for this program is Earl Nightingale's "The Strangest Secret", Napoleon Hill's "Think and Grow Rich", James Clear's "Atomic Habits" and other personal development programs. These books always have these "every day, you should X" (meditate, write your goals, etc) - and I became frustated - Just how many "things" are you "supposed" to do per day, and how do they fit together, and how can you create helpful reminders & to turn these into habits? So far, I've been testing the system on myself, and it's been a HUGE help towards giving purpose to my life and day, and reducing feelings of depression & insecurity.

The solution is completely open-source (useable as web app, local docker container, and installable on a stand-alone computer - which I recommend), and I'll also soon offer it as a for-pay service.

If anyone is interested in these projects, I welcome contributors!

// JRO

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

#566

Post by shalzuth »

I’m finally trying to jump on the AI train for a long ride instead of getting off at the first stop.

I’m currently creating a new fan site for Marvel Rivals (https://marvelrivals.app), and I’m trying to introduce new types of features using predictive analysis, and further, use some DL maybe to understand specific player behavior and do stuff like find cheaters. I am failing so far.

I thought it’d be easier to throw data at the magic AI monster, but it’s still garbage in -> garbage out. It makes me respect AI engineers a lot more.

I wish there was an easier way to apply AI to this kind of stuff, on the how to do better data analysis. Ideally, I’d hook up some tool to my Postgres db, which has a couple tables but everything is named appropriately and has references. Then the tool would output correlations, patterns, stuff people would find useful and interesting. Instead, right now, I think I have to make those guesses and then build models that will either support my hypothesis or reject it, but I don’t know ahead of time and it relies on my gut feelings.

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

#567

Post by tempado590 »

I was creating this anonymous confession posting site with a 4chan like interface. [7shin](https://7shin.vercel.app) and today i just created an archive sort of thing called the-image-web. Basically I wanted to create a wall of images uploaded by people on the internet. [theimageweb](https://theimageweb.vercel.app)

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

#568

Post by AJRF »

chandureddyvari wrote: post #291
AJRF wrote: post #127

I recently made a little tool for people interested in running local LLMs to figure out if their hardware is able to run an LLM in GPU memory. https://canirunthisllm.com/

Neat idea! It would be helpful to have LLMs ranked from best to worst for a given GPU. Few other improvements I can think of: - Use natural language for telling offloading requirements. - Just year of the LLM launch of HF url can help if it’s an outdated LLM or a cutting edge LLM. - VLMs/Embedding models are missing?

Hey - thanks for the reply.

  - Use natural language for telling offloading requirements.
Do you mean remove the JSON thing and just summarise the offloading requirements?

  - Just year of the LLM launch of HF url can help if it’s an outdated LLM or a cutting edge LLM.
Great Idea - I will try add this tonight.

  - VLMs/Embedding models are missing?
Yeah I just have text generation models ATM as that is by far where the most interest is. I will look at adding other model types in another type, but wouldn't be until the weekend that I do that.

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

#570

Post by lennertjansen »

I'm working on Airweave https://github.com/airweave-ai/airweave , an open-source dev tool that makes any app searchable for AI agents. it connects to a source app, db, or api and converts its contents to accessible knowledge for agents. Airweave automates authentication, ingestion, enrichment, mapping, and syncing to vector stores and graph databases of choice. you can use it via our UI, API, or SDKs https://docs.airweave.ai/

we originally built this for our previous agent startup as an internal solution to ensure agents could find the relevant data on apps they're using. We then pivoted to this after some early positive reactions and decided to open-source it.

here's a short demo: https://tinyurl.com/demo-airweave

we're two engineers/friends based in Amsterdam, NL. We just launched the project, so it's rough around the edges ofc, but we're very eager to get some feedback!

feel free to reach out to me personally if you like this! - https://www.linkedin.com/in/lennertjansen/ - https://x.com/lennertjansen

Post reply on HN