561–570 of 773 posts
It's a puzzle game -- numbers on a board -- where the gap between numbers dictates the arithmetic operation done to them.
The goal is to use all the spaces on the board to make sums of 12.
Have shared it a few times on HN already, but keen to hear from anyone who hasn't tried it yet!
Fluir, a web app that improves Spanish speaking beyond A2 https://getfluir.app I hit a plateau with my learning, having used Duolingo + tutor. It was only until I tried to read a book that I felt like I was making real progress. Highlighting words in Kindle, exporting them to Anki, then feeding back my progress to my tutor was fiddly and not a good use of my time. Also practicing my speaking once a day wasn't enough.…
Edit: And a second question: do you support exporting the studies vocabulary as Anki or csv/…?
AI can make a good one-off character, but keeping that same character consistent across dozens of product illustrations is still surprisingly difficult. That’s the problem I’m trying to solve.
Would love any feedback.
[HUMAN-CODE] I'm building a video game. It's part Valheim, part Ultima IV: https://stravaeger.com/ You can play the demo in the browser now (mobile as well as desktop), but I'll be packaging it up for Steam soon. It's all vanilla javascript, html and css. No AI, no 3rd party game engine, no build system even, and just a couple external dependencies for things like networking that I didn't want to reinvent myself. It'…
Mostly this week I’ve been wrestling with a better solution to filtering openrouter providers because a common failure mode is getting stuck on one which is either very slow, or doesn’t actually meet the spec it promises in terms of tool calling.
I’ve carried on working on my llm powered book recommendation engine, Leafle (try it out if you like! https://leafle.nanosheep.net ). Mostly this week I’ve been wrestling with a better solution to filtering openrouter providers because a common failure mode is getting stuck on one which is either very slow, or doesn’t actually meet the spec it promises in terms of tool calling.
https://github.com/kulvind3r/GamingGaiden
Created this to replace the original Gameplay Time Tracker which was closed source and abandoned. Been improving and maintaining it for 3+ years now and it has found moderate audience in it's niche.
It lets you build apps and features that work natively across web, desktop and mobile, streaming from your backend into your client app, letting you deploy changes instantly.
A Hypen client can be any app that includes Hypen SDK, letting you render apps inside apps, build backend-driven features or create a mini-app platform like WeChat.
The framework supports many languages, such as TS, Rust, Go, Kotlin, Swift and pretty much any language that can run WASM or interop with native.
--
To give you a taste, some things in the upcoming release changelogs are:
- Performance improvements brining the web client on par with React (even faster in some cases)
- Exposing states and actions to agents, letting agent drive the app directly instead of through UI
- First class drag/drop support with pinning as a primitive
And some recently released things:
- First class accessibility support, with out of the box inference and minimal intervention
- Animation support with simple DX for animations, scrubbing, state and screen transitions
- Video component and a whole Netflix clone Hypen app example
- UI Testing suite so you can easily preview how your app looks like across devices
Next up on the feature list will be device communication and permissions, Android TV support, theming and external component installation, letting you build shared component packs and primitives.
I use Claude Code and Codex for coding but don't want my regular chats in those apps. I prefer to keep all my chats in one place so I can go back and search easily, that is why I built Vinaa.
Nowadays I'm more curious about how I can use AI for marketing. I'm experimenting it with building an SEO agent system
It's an approach to defensive security for software products (especially smaller companies) by acting as the security team you don't have/can't afford. It does security recon/analysis, etc via AI.
I got tired of all of the LLM labs building firewalls of "oh, nobody is allowed to do security research/find+fix vulnerabilities in their software unless they apply for special registration."
Instead of saying "oh, anything that the model determines is security research is a vulnerability threat", it does reliably enforceable analysis like "look for a TXT record in DNS the same way a SSL provider would ensure you own the property". So it can do "live" penetration tests against your infrastructure if you provide authorization
It handles things like incoming "security researcher" e-mails to cut down on the noise of nonsense vulnerability reports by acting as your security team that defends against the reports
It provides provable/signed attestation that a pentester has checked your code/live infrastructure/APIs/etc and validated them, and/or has done a check after you've remediated whatever issues that were found. It helps all 3 sides of the "company needs pentester" and "pentester" and "auditor"/"customer" to come to agreements on what's important and what's been solved