brianhabana123 · HN

TensorRT-LLM running natively on Windows (no WSL)

@svpino · X

You can check out Runpod here: Thanks to the Runpod team for partnering with me on this post.

Wan3Pro — AI 在线视频生成工具

cdnsteve · HN

Tokenstead, find AI models for your hardware

dev_dan_2 · HN

WatchMachineGo – A visualizer to show hardware performing LLM inference

@DeCaveApp · X

hannesfur · HN

Stillwind – PCB part selection as constraint solving

@rand_monsterlab · X

A monster walks into a GPU-simulated pond. Reactive SPH water in the browser with @threejs + WebGPU. Every movement sends ripples through Coming soon. Follow @rand_monsterlab: #ThreeJS #WebGPU #VibeCoding #IndieGame #Monster

dylansuttonc · HN

When I started programming Edge Python more than six months ago, I was looking for a version of Python that weighed less than 200 kb so it could reach any device, sandboxed by design, built with browsers in mind, decoupled from the operating system and very fast. Today the closest competitor would be MicroPython. However, it did not solve my real problems or the problems of the people who use the project. * Managing async and blocking code on the event loop. MicroPython inherits CPython's blocki

micstradev · HN

I made a strategy game where you play the US or China through the AI race, 2026 to 2030, sixteen quarterly turns in the browser. One run takes about half an hour. At the start, the game seals two dice you never get to see. Inside: how hard alignment really is, and how fast takeoff compounds. You get eval reports, but only as ranges, and they flatter you most exactly when your systems are least aligned. At the end you get a debrief which shows what your evals said each quarter and also what was actually true. I lost every run I played myself so far. Every number in the game is source-backed or a labeled design choice. Some of them are wrong somewhere. There is an issue template for challenging a number with a better source, and the better source wins. No accounts, no tracking, no server, works offline after first load. AGPL, nonprofit. Cards and parameters are plain JSON. Contribution is possible without writing code. Would like to have your thoughts if it is fun to play, how you lik

littlepp · HN

MiniMax H3 – Turn text and images into AI video clips

@dorikuio · X

AI agents have amnesia — Claude Code figures out the codebase, an hour later Codex starts from zero. So I built a shared memory + task board for every MCP agent — Claude Code, Codex, Cursor, Gemini CLI: Is this just my problem? Help me find out.