Ask HN: What are you working on? (April 2025)
971–980 of 1001 posts
Re: Ask HN: What are you working on? (April 2025)
#972Re: Ask HN: What are you working on? (April 2025)
#973I’m also working on the next version of HacKit, a macOS Hacker News reader focused on simplicity, performance and adherence to macOS design language. It’s already available on the App Store: https://apps.apple.com/app/id1549557075 and further information can be found here: https://github.com/anosidium/HacKit-Feedback-And-Support.
I’d be delighted to hear any feedback, suggestions, or ideas — or simply to connect with others working on Apple platform development.
Re: Ask HN: What are you working on? (April 2025)
#974I have been working on http://phrasing.app - a language learning & acquisition tool for polyglots. I’ve been using it to study ~12 languages (5 on maintaince, 2 seriously studying, 5 casually “studying”) and it’s starting to feel really good. If anyone is learning/maintaining several languages, please reach out! I’m looking for beta testers in as many languages as possible (it supports 120+). In what I believe is sti…
I'm just getting popups asking me to set up my language, but... where?? It needs a most intuitive UI. :3
Re: Ask HN: What are you working on? (April 2025)
#975demo video - https://www.dropbox.com/scl/fi/bv9vhagugpuz3mhc089mz/ScreenR...
Re: Ask HN: What are you working on? (April 2025)
#976Re: Ask HN: What are you working on? (April 2025)
#977[1]ʻŌlelo Honua:
[2] Foil Sim:
Re: Ask HN: What are you working on? (April 2025)
#978Re: Ask HN: What are you working on? (April 2025)
#979Re: Ask HN: What are you working on? (April 2025)
#980long story short: i built a system that scrapes a company’s site, profiles, press, and anything else it can find online, then runs it through a multi-model prompt engine i wrote from scratch (multiple LLMs chained together with custom logic). the workflow is split into three parts: crawl, process, synthesize.
output comes in markdown. all signal, no bs. useful for GTM, growth, competitor analysis, product gaps, strategic blindspots, that kind of thing.
i’ve been stress testing it on real companies. just pushed 2 sample reports to GitHub if you wanna peek:
- Grab (SEA unicorn) - LemmyHomes (early-stage Malaysian proptech)
→ https://github.com/lightyoruichi/numen-output
not selling it as a product (yet). backend still in dev. just doing reports manually for now while testing edge cases/validating if anyone wants this at all lol.
note: it’s not fully automated. i use the system to generate raw analysis, then apply human input to reframe, expand, or clean up weak insights. think of it like pairing with an AI researcher who works fast but lacks nuance/context, you still need a strategist to shape the output. there's tons more feature but at the core this is it.
happy to run one or two more this week if anyone wants a teardown. not free though (token cost’s brutal lol). DM if interested.