Category · last 30 days
AI
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Open-source unified interface for agent harnesses
AI · 21d ago · harnessrouter.ai
Hello everyone. I've been working on this experimental editor called Huzzah. I've been working almost exclusively with coding agents since January of this year, and over the past few months I began to feel utterly exhausted by them. They're great, but I'm finding it more and more tedious to write full sentences for every change I want. Not only that, but it seems there's a complexity limit for codebases - beyond a certain point the agent begins confusing itself. I'd like to go back to writing code, but I don't want to go all the way back to fully manual coding. So I've come up with this…
AI · 16d ago · danielvaughn.dev
Your AI coworker gets a computer. You get your day back.
AI · 14d ago · construct.computer
ChatCut Desktop▲290Video editor built for humans & AI. Edit with GPT & Claude.
AI · 11d ago · chatcut.io
Human Behavior▲273Product analytics told you what happened. We handle it.
AI · 24d ago · humanbehavior.co
Find and remove every trace AI leaves in your text
AI · 18d ago · claudewatermark.xyz
FetchSandbox MCP▲263The MCP that proves your AI's integration fixes work
AI · 14d ago · fetchsandbox.com
Turn form data into insights and action with AI
AI · 12d ago · jotform.com
Nitro 4.0▲240The first human translation platform built for AI agents
AI · 30d ago · nitrotranslate.com
Hi HN, we built an open source model gateway. It's a single place to manage our own self hosted, frontier, and open source models in one place. It’s is rust native, built for concurrency, and implements all the config quirks across models and providers (streaming formats, tool calls, model parameters, rate limits, and different error behavior). The gateway adds under 1 ms for BYOK requests and under 2 ms when Experiential supplies the provider key. It has every major inference provider, and 1000+ models refreshed daily via a codex agent that opens a PR. Compared to other similar projects…
AI · 9d ago · github.com
From video to publish-ready AI subtitles—all in one browser
AI · 15d ago · subtitlegenerator.app
A MagSafe AI Recorder That Acts for You
AI · 27d ago · shop.genspark.ai
Hey HN! I'm excited to show off this really fun project I put together. I originally built this project 2-3 years ago, AI was already booming at the time, however voice AI agents were still very early. I loved my proof of concept at the time, but wasn't quite happy with it. I recently had the desire to check out the tech again, and know many of you will be interested. Interviews are speech to speech with OpenAI's gpt-realtime-2.1 over WebRTC. This model is... expensive, and because of that, I have to add some amount of restrictions, conversations are tied to a authenticated Clerk user id. I…
AI · 27d ago · whodunnitai.com
