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

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

news.ycombinator.com

Post reply on HN
Print view View original

301–310 of 1001 posts

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

#301

Post by ttruett »

I'm building decision-making software: https://orgtools.com

Not sure what the market is for something like this but it's something I've been thinking a lot about since stepping down as CEO of my previous company.

My goal is two-fold:

1. Help teams make better, faster decisions with all context populating a source-of-truth.

2. Help leaders stay eyes-on, and circumstantially hands-on, without slowing everything down. What I'd hope to be an effective version of "Founder Mode".

If anybody wants to play around with it, here's a link to my staging environment:

https://staging.orgtools.com/magic-share-link/5a917388cf19ed...

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

#302

Post by netcoyote »

I'm playing around with sandboxing techniques on Mac so I can isolate AI tools and prevent them from interacting with files they shouldn't have access to -- like all my dotfiles, AWS credentials, and such.

I've created two open-source solutions, one which uses a VM (https://github.com/webcoyote/clodpod) and another which creates a limited-user account with access to a shared directory (https://github.com/webcoyote/sandvault).

Along the way I rolled my own git-multi-hook solution (https://github.com/webcoyote/git-multi-hook) to use git hooks for shellcheck-ing, ending files with blank lines, and avoid committing things that shouldn't be in source control.

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

#305

Post by cjflog »

neilv wrote: post #196
cjflog wrote: post #31

Currently a one-man side project: https://laboratory.love Last year, PlasticList found plastic chemicals in 86% of tested foods—including 100% of baby foods they tested. Around the same time, the EU lowered its “safe” BPA limit by 20,000×, while the FDA still allows levels roughly 100× higher than Europe’s new standard. That seemed solvable. Laboratory.love lets you crowdfund independent lab testing of the specific p…

1. An example result is " https://laboratory.love/product/117 ", which is a list of chemicals and measurements. Is there a visualization of how these levels relate to regulations and expert recommendations? What about a visualization of how different products in the same category compare, so that consumers know which brand is supposedly "best"? Maybe a summary rating, as stars or color-coded threat level? 2. If you f…

Thank you for your questions!

1. I'm still working to make results more digestible and actionable. This will include the %TDI toggle (total daily intake, for child vs adult and USA vs EU) as seen on PlasticList, but I'm also tinkering with an even more consumer-friendly 'chemical report card'. The final results page would have both the card and the detailed table of results.

2. I have not found any regulation-violating levels yet, so in some sense, I'll cross that bridge when I get there. Part of the issue here is that many believe the FDA levels are far too relaxed which is part of why demand for a service like laboratory.love exists.

3. This is part of the challenge that PlasticList faced, and additionally a lot of my thinking around the chemical report card are related to this. Some folks think a single test would be sufficient to catch major red flags. I think triplicate testing is a reasonable balance of statistically robust while not being completely cost-prohibitive.

4. Yes, I suppose one could do that, as long as the funded products can be acquired by laboratory.love anonymously through their normal consumer supply chains. Laboratory.love merely acquires three separate batches of a given product from different sources, tests them at an ISO/IEC 17025-accredited lab, and publishes the data.

5. I suppose any project can be shut down by a lawsuit, but laboratory.love is not currently breaking any laws as far as I'm aware.

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

#306

Post by thethimble »

netcoyote wrote: post #302

I'm playing around with sandboxing techniques on Mac so I can isolate AI tools and prevent them from interacting with files they shouldn't have access to -- like all my dotfiles, AWS credentials, and such. I've created two open-source solutions, one which uses a VM ( https://github.com/webcoyote/clodpod ) and another which creates a limited-user account with access to a shared directory ( https://github.com/webcoyote…

Have you considered using docker? Seems possibly more lightweight than a VM with more isolation than a user account based method.

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

#307

Post by netcoyote »

thethimble wrote: post #306
netcoyote wrote: post #302

I'm playing around with sandboxing techniques on Mac so I can isolate AI tools and prevent them from interacting with files they shouldn't have access to -- like all my dotfiles, AWS credentials, and such. I've created two open-source solutions, one which uses a VM ( https://github.com/webcoyote/clodpod ) and another which creates a limited-user account with access to a shared directory ( https://github.com/webcoyote…

Have you considered using docker? Seems possibly more lightweight than a VM with more isolation than a user account based method.

Yes, I've used docker and podman. They're great. But I wanted to be able to run Xcode and IOS simulator, which requires macOS, so developed these solutions.

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

#308

Post by bryanhogan »

I'm making an app for self-tracking. Combining elements from habit trackers, health logging and journaling. Built for rich customization and local-first. Want to be free of rigid structures of many existing apps while providing a better UX / usability than using a spreadhsheet.

Updated the landing page just yesterday!

Landing page + waitlist: https://dailyselftrack.com/

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

#309

Post by Franklinjobs617 »

scubbo wrote: post #296
Franklinjobs617 wrote: post #289

I’m currently building YTVidHub—a tool that focuses on solving a very specific, repetitive workflow pain for researchers and content analysts. The Pain Point: If you are analyzing a large YouTube channel (e.g., for language study, competitive analysis, or data modeling), you often need the subtitle files for 50, 100, or more videos. The current process is agonizing: copy-paste URL, click, download, repeat dozens of t…

How coincidental - I needed exactly this just a couple days ago. I ended up vibecoding a script to feed an individual URL into yt-dlp then pipe the downloaded audio through Whisper - not quite the same thing as it's not downloading the _actual_ subtitles but rather generating its own transcription, but similar. I've only run it on a single video to test, but it seemed to work satisfactorily. I haven't upgraded to bul…

That is some fantastic validation, thank you! It’s cool to hear you already vibecoded a solution for this.

You've basically hit on the two main challenges:

Transcription Quality vs. Official Subtitles: The Whisper approach is brilliant for videos without captions, but the downside is potential errors, especially with specialized terminology. YTVidHub's core differentiator is leveraging the official (manual or auto-generated) captions provided by YouTube. When accuracy is crucial (like for research), getting that clean, time-synced file is essential.

The Bulk Challenge (Channel/Playlist Harvesting): You're spot on. We were just discussing that getting a full list of URLs for a channel is the biggest hurdle against API limits.

You actually mentioned the perfect workaround! We tap into that exact yt-dlp capability—passing the channel or playlist link to internally get all the video IDs. That's the most reliable way to create a large batch request. We then take that list of IDs and feed them into our own optimized, parallel extraction system to pull the subtitles only.

It's tricky to keep that pipeline stable against YouTube’s front-end changes, but using that list/channel parsing capability is definitely the right architectural starting point for handling bulk requests gracefully.

Quick question for you: For your analysis, is the SRT timestamp structure important (e.g., for aligning data), or would a plain TXT file suffice? We're optimizing the output options now and your use case is highly relevant.

Good luck with your script development! Let me know if you run into any other interesting architectural issues.

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

#310

Post by NiloCK »

My on again, off again life's work has been a foss dev stack for interactive tutoring systems. Something like a general purpose Math Academy, with mechanics to permit UGC and courses that are both adaptive (to the user's background and demonstrated skill) and inter-adaptive (to the userbase's expressed priorities).

http://github.com/patched-network/vue-skuilder, docs-in-progress at https://patched.network/skuilder

I am using this stack now to build an early literacy app targeting kids aged 3-5ish at https://letterspractice.com (also pre-release state, although the email waitlist works I think!). LLM assisted edtech has a lot of promise, but I'm pretty confident I can get the unit cost for teaching someone to read down to 5 USD or less.

Post reply on HN