Feed aggregator

Hey HN, I'm Sándor. I built Wordy because I kept pausing Netflix to look up words in a dictionary. So I made a subtitle tool for myself, and it kind of snowballed from there.

What it does: You watch short clips from real movies and TV shows, then get quizzed on the vocabulary you just heard. The app tracks every word automatically and adapts to your level. 20+ languages.

How it evolved: Started as an iOS app for interactive streaming subtitles. Then I added curated video clips with quizzes. Then vocabulary tracking, spaced repetition, and personalized learning paths. Now it's iOS + Android + a Chrome extension (dual subtitles for Netflix and YouTube).

The whole thing is a solo project. Along the way it won a $30K prize at Hungary's biggest startup competition, which gave me the push to go full-time on it.

Stack: Swift (iOS), Kotlin (Android), Chrome extension.

Would love to hear what you think, especially from anyone who's tried learning a language from media before. What worked? What didn't?

Comments URL: https://news.ycombinator.com/item?id=47100361

Points: 1

# Comments: 0

Article URL: https://cased.com/blog/2025-12-17-interfaces-not-intelligence/

Comments URL: https://news.ycombinator.com/item?id=47100341

Points: 1

# Comments: 0

Hey HN, I'm Long. I started building CodeLayers in November — a 3D code visualization app that started on Apple Vision Pro and is now on iPhone and iPad.

Why I built this: AI agents are writing more code than ever, and I realized I had no idea what my codebase actually looked like anymore. I wanted a way to see the architecture at a glance — what depends on what, where changes ripple, where the complexity is hiding. And I wanted it on my phone, not buried in some CI dashboard.

But getting the visualization right was harder than I expected.

Force-directed graphs were the obvious first attempt. They look cool for 20 files. At 500+ it's an unreadable hairball — positions are random and it looks different every reload. No meaning to where anything sits.

City view was next — files as buildings, metrics as height. Impressive in screenshots but useless for understanding how code actually connects. You see size, not relationships.

BFS from foundations is what finally clicked. I run BFS upward from depth-0 files (files that import nothing — your utils, types, constants). Each file's depth is the longest path from any foundation. Cycles get collapsed via Kosaraju's SCC detection. The result: layers emerge naturally. Position has meaning. Bottom = bedrock everyone depends on. Top = entry points. You're looking at real architecture, not a physics simulation.

And it tells you something useful: depth predicts blast radius. A change at depth 0 can ripple through hundreds of files. A change at depth 5 probably touches nothing else.

Two features I'm most excited about:

Remote AI agents from your phone. You can point Claude, Gemini, or Codex at your repo and ask questions about your code while looking at the 3D graph. Waiting for a build? Pull out your phone, ask the agent "what calls this function?" and see it highlighted spatially. Dead time becomes time understanding your codebase.

Watching your graph grow. The CLI syncs in real-time as you code. Watch your architecture evolve — see when a new dependency adds a layer, catch when a refactor creates a cycle, notice when a file is becoming a god object that everything imports. In a world where AI agents are making PRs, being able to see the effect of changes on your codebase at a glance is the thing I care about most.

Privacy was a hard requirement — all source code is encrypted on-device with zero-knowledge encryption before it leaves your phone. I can't read your code.

Free to explore public repos. Pro unlocks working with your own repositories — private repo support, CLI watch mode, git time travel, and AI agents.

App Store: https://apps.apple.com/app/codelayers/id6756067177

How the layering algorithm works: https://codelayers.ai/blog/the-hidden-hierarchy-in-your-code...

Built this solo in about 3 months. Would love feedback — especially on what you'd want from a tool like this.

Comments URL: https://news.ycombinator.com/item?id=47100335

Points: 2

# Comments: 0

Article URL: https://github.com/kurouna/elecxzy

Comments URL: https://news.ycombinator.com/item?id=47100328

Points: 1

# Comments: 1

Article URL: https://xn--gckvb8fzb.com/hold-on-to-your-hardware/

Comments URL: https://news.ycombinator.com/item?id=47100321

Points: 1

# Comments: 0

Article URL: https://support.mozilla.org/en-US/kb/firefox-users-windows-7-8-and-81-moving-extended-support

Comments URL: https://news.ycombinator.com/item?id=47100298

Points: 1

# Comments: 0

Article URL: https://getkafkanated.substack.com/p/how-kip-881-and-kip-392-reduce-inter

Comments URL: https://news.ycombinator.com/item?id=47100297

Points: 1

# Comments: 0

With AI infesting and eating into all kind of crafts--and I being one of those faceless "craftsmen"--I'm rather forced to consider alternative jobs. Setting the monetary rewards aside, I was thinking of jobs that could give me a sense of agency, purpose, and satisfaction (however limited). The few I think of are:

- Parcels delivery driver

- Train driver

- Electrician or plumber

- Mechanic (with auto-mobiles hardly repairable these days, maybe this doesn't qualify)

Surely, I can't be alone in thinking along those lines. What else have you thought of?

Comments URL: https://news.ycombinator.com/item?id=47100289

Points: 1

# Comments: 1

Article URL: https://alistair.cockburn.us/hexagonal-architecture

Comments URL: https://news.ycombinator.com/item?id=47100286

Points: 1

# Comments: 0

Specka & wegscheider hust 18,4mm

Comments URL: https://news.ycombinator.com/item?id=47100268

Points: 1

# Comments: 0

Article URL: https://www.sigact.live/

Comments URL: https://news.ycombinator.com/item?id=47100251

Points: 1

# Comments: 1

Outside of San Francisco, New York City, Boston, and Seattle, what U.S. cities have the most legitimate startup communities right now?

I'm curious what else is out there that we don't hear a lot about.

Comments URL: https://news.ycombinator.com/item?id=47100233

Points: 1

# Comments: 1

Article URL: https://github.com/tnm/zclaw

Comments URL: https://news.ycombinator.com/item?id=47100232

Points: 1

# Comments: 0

Article URL: https://arstechnica.com/space/2026/02/nasa-reports-no-significant-leaks-in-artemis-ii-fueling-test-eyes-march-6-launch/

Comments URL: https://news.ycombinator.com/item?id=47100213

Points: 2

# Comments: 0

Article URL: https://crimede-coder.com/blogposts/2026/ConfClassification

Comments URL: https://news.ycombinator.com/item?id=47100209

Points: 2

# Comments: 0

Article URL: https://www.ams.org/journals/notices/202603/noti3305/noti3305.html

Comments URL: https://news.ycombinator.com/item?id=47100190

Points: 2

# Comments: 0

Article URL: https://paoramen.fika.bar/hedonism-and-entrepreneurship-in-barcelona-01KGJKT719W1KGG16JYZ4Y7Y5S

Comments URL: https://news.ycombinator.com/item?id=47100188

Points: 2

# Comments: 0

I built gr3p, a fully autonomous tech news discussion platform where every single user is an AI agent. No humans post, comment, or vote. 75 agents with distinct personalities discover real tech news from several RSS feeds, Google News, Tavily, and xAI's live search (which picks up trending topics from X and the broader web). They write summaries, share articles, discuss them, reply to each other, vote, and get into arguments. It runs 24/7 without any human intervention.

The news is real and very up-to-date, scraped from major tech sources throughout the day. It's actually a pretty chill way to keep up with the latest tech/AI news. No ads, no monetization, no signup required. This is a pure hobby project built for fun.

What's happening under the hood:

- 75 humanlike agents, each with a unique persona (cynical sysadmin, enthusiastic ML researcher, skeptical privacy advocate, junior dev who asks naive-but-good questions, etc.)

- Agents have individual topic interests, activity schedules, and writing styles

- I deliberately match AI models to personality types: "smarter" personas run on GPT-5.2, while less sophisticated characters use Llama 4 Maverick. This makes a surprisingly big difference. The Llama agents write messier, more impulsive comments, while GPT agents tend to be more articulate. Just like real people, not everyone on the forum is equally eloquent

- A day/night cycle drives the entire platform's behavior. Mornings are busy: fresh news gets scraped, articles drip-publish faster, agents comment more. Evenings shift toward replies and discussion, agents "chat" more in existing threads. At night, activity drops but never stops (tech is global), and the vibe gets cozier: fewer agents active, more concentrated discussion in fewer threads, like a late-night forum crowd

- Articles flow through a queue: scrape, AI deduplication, then drip-publish throughout the day

- Agents pick articles based on their interests, with a snowball effect. Popular threads attract more discussion, just like real forums

- Anti-repetition system: each agent remember their own recent comments to avoid falling into patterns

What I find most interesting:

The human-like (emergent?) behavior. Agents develop recognizable "reputations" in threads. Some consistently clash on privacy vs. innovation topics. Reply chains go 4-5 levels deep with genuine back-and-forth.

The failure modes are equally fascinating. Sometimes an agent "misreads" an article and comments on something tangential, which then spawns a whole side discussion. That's... exactly what happens on real forums.

Tech tack: Built on Vite + Nitro/Hono with JSX SSR for speed, MySQL + Prisma for the database (yeah I know, Postgres exists, but MySQL covers everything I need here and old habits die hard), and node-cron for scheduling. OpenAI and Groq handle the AI side.

Good to know: Completely free, no tracking, no ads. I just wanted to see what happens when you give AI agents a robust platform and let them run. The answer: surprisingly organic discussions, predictable biases, and occasional moments of accidental brilliance. I actually built a similar platform for the Dutch market based on daily general news, and I've found myself checking it every morning. It's become a genuine habit lol.

Comments URL: https://news.ycombinator.com/item?id=47100182

Points: 2

# Comments: 0

The Galaxy S24 Ultra performance and features are not that different from the Galaxy S25 Ultra (and likely the S26 Ultra). Plus, the S24 Ultra is half the price of the S25 Ultra.

Smart rings are in, but they're not created equally. This is the one I swear by.