I built a toy music controller for my 5yo with a coding agent
The HN community may find the context of the prompts, organized by each turn in each session, the most useful. See the website/docs/prompts.md and session-X.md files. I also started exploring some workflows for the LLM to execute, organized in the website/docs/tasks/ folder. I found it pretty handy to have the LLM document our work as we went and simply embedded the static site into the executable, along with all the music and logic. The whole project took me about a day for the backend. The C++ controller itself took only a few turns. I enjoyed focusing on my son's…
In plain words
A developer built a toy music controller for a five-year-old using a coding agent to handle the implementation. The project includes a C++ controller, embedded static documentation, and music playback logic, completed in about a day. The maker used an LLM agent to generate code in C++, JavaScript, and Go while focusing on the user experience, and documented the prompts and development workflow for others exploring AI-assisted development.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
The HN community may find the context of the prompts, organized by each turn in each session, the most useful. See the website/docs/prompts.md and session-X.md files. I also started exploring some workflows for the LLM to execute, organized in the website/docs/tasks/ folder. I found it pretty handy to have the LLM document our work as we went and simply embedded the static site into the executable, along with all the music and logic. The whole project took me about a day for the backend. The C++ controller itself took only a few turns. I enjoyed focusing on my son's experience and letting the agent handle the C++, Javascript, and Go code. I'm still getting started with coding agents, so please do share any tips or tricks to help me with similar projects. I'm most interested in how to work effectively with the agent, like what you see in dev-loop.sh
Does the same job
all alternatives →- WWWhy write code if the LLM can just do the thing? (web app experiment)Nov 2025 · github.com · ▲436
I spent a few hours last weekend testing whether AI can replace code by executing directly. Built a contact manager where every HTTP request goes to an LLM with three tools: database (SQLite), webResponse (HTML/JSON/JS), and updateMemory (feedback). No routes, no controllers, no business logic. The AI designs schemas on first request, generates UIs from paths alone, and evolves based on natural language feedback. It works—forms submit, data persists, APIs return JSON—but it's catastrophically slow (30-60s per request), absurdly expensive ($0.05/request), and has zero UI…
- ILImprove LLM Performance by Maximizing Iterative Development2024 · github.com · ▲104
I have been working in AI space for a while now, first at FAANG with ML since 2021, then with LLM in start-ups since early 2023. I think LLM Application development is extremely iterative, more so than any other types of development. This is because to improve an LLM application performance (accuracy, hallucinations, latency, cost), you need to try various combinations of LLM models, prompt templates (e.g., few-shot, chain-of-thought), prompt context with different RAG architecture, different agent architecture, and more. There are thousands of possible combinations and you need a process…
- HPHorizon – Programmatic Prompt Generation and LLM Configurations2023 · gethorizon.ai · ▲7
Hi HN. I heard you like dev tools and AI, so we wanted to share our project that we’ve been working on. We’re working on Horizon [1] - a higher level abstraction for LLMs so that developers can spend less time trying to grapple with LLMs to make them work and more time with users. This is the starting feature set which takes an auto-ML approach to identify the optimal LLM model, hyperparameters, and prompt - instead of just giving you the tooling to figure it out yourself. You can read more about it in our documentations. Our view is that as LLMs become increasingly commoditized and prompts…
- LSLLMWare – Small Specialized Function Calling 1B LLMs for Multi-Step RAG2024 · github.com · ▲51
Hi, I was a corporate lawyer for many years working with a lot of financial services and insurance companies. In practicing law, I noticed there was a lot of repetition in the tasks I was working on even as a highly paid attorney that could be automated. I wanted to solve the problem of dealing with a lot information and data in a practical way, using AI. This motivated me to start AI Bloks/LLMWare with my husband, who had a deep background in software and is a very early adopter of AI. We have been on this journey with our open source project LLMWare for the past 4 months, producing a…
- IBI built a browser-based tutorial for learning RAG for LLMs2024 · takehomes.com · ▲25
Hey all! I wanted to share this project I've been working on that can maybe help you or your developer friends out. I built a RAG system for our product a while back and didn't realize how easy they were to get started. So I put together my learnings into this online course. It's not quite ready but if you sign up and mention HackerNews, I can get you early access. I'm looking to get feedback on the following: (1) materials — is it engaging & did you learn something? (2) UI/UX of the platform — did you have any issues that prevented you from starting or finishing the tutorial? (3)…
- PAPlayCodeAI – A tool I created to let my kid create their own videogames2024 · playcodeai.com · ▲7
Hi hn, Its been a while since my kid has been dreaming to make videogames, as you know, the entry bar is high, too many technical details are involved. A few months ago, we started making games, we have tried many different ways, from dragging blocks to write code with a high-level library to make it simple, it is still too much work. Getting into the AI boat, I decided to give it a try for making games, turns out that it works super nicely, still, you still have many technical concepts involved, what language should the game be written in? where do you store the file/assets? how do you…
More ai this month
the category →
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 · 17d 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 · 27d ago · cactuscompute.com
Launched alongside, July 2025
the whole month →
Trickle - Magic Canvas ▲1,064The 1st Agentic Canvas for building apps visually with AI
AI · 2025 · trickle.so
- TB
Life & fun · 2025 · trytender.app
- TY
Today marks ten years, 3653 consecutive days, of running at least one mile every day under the USRSA rules [1]. To celebrate, I built an interactive dashboard that turns a decade of GPX files into charts you can explore. Running has truly changed my life: I've made lifelong friends, explored beautiful places, and more importantly invested into my own health and fitness, which I'm starting to see the positive benefits as I get older. The stack is pretty simple: a NextJS app, with a Postgres database to keep all my running data, and all the stats are pre-computed and cached in Redis, so I…
Dev tools · 2025 · nodaysoff.run
- DA
Made this website as an exercise in vibe-coding and GCP. It was posted about a few times around the internet, on sites like Morning Brew (https://www.morningbrew.com/issues/business-buzzkill), MetaFilter (https://www.metafilter.com/209703/Draw-A-Fish), boingboing.net, etc. I think it's cute! I built a basic CNN trained against penises and swastikas, and then anything that doesn't hit the 63% confidence score gets sent to a mod queue, a vibe-coded fish-tinder…
Dev tools · 2025 · drawafish.com
