BabyStepsJs – Interactive Skill Tree for Babies in a Single HTML File
Hi HN, I built BabyStepsJs to track the development of my newborn daughter in the form of a skill tree. It’s a mix of gamified documentation of her current progress and a bit of education on what she might discover next. I conducted a similar development experiment a few months ago with the same rules (see the cs-util-com/InstantScribe repo): - Act mainly as the PM and QA for the AI (this time ChatGPT-o1) and iteratively add user stories and requirements to extend the feature set. - Each iteration was typically a single commit, so the AI’s proposed changes were easy to review in the git…
What it does
In the maker’s words, at launch
Hi HN, I built BabyStepsJs to track the development of my newborn daughter in the form of a skill tree. It’s a mix of gamified documentation of her current progress and a bit of education on what she might discover next. I conducted a similar development experiment a few months ago with the same rules (see the cs-util-com/InstantScribe repo): - Act mainly as the PM and QA for the AI (this time ChatGPT-o1) and iteratively add user stories and requirements to extend the feature set. - Each iteration was typically a single commit, so the AI’s proposed changes were easy to review in the git diff. - I generally did not modify the code much myself, only making minor adjustments like tweaking colors, positions, etc. - I also made some initial high-level decisions, such as choosing D3 for the graph. Some findings/impressions from that process: - I was able to prototype this in a few hours. The process was fun and allowed me to change requirements as I learned more about what I wanted. - Most of the changes were correct on the first try (using o1). With other models, I often noticed more random changes in unrelated parts of the app. - o1 tends to strip comments, even when they provide useful context on what the code does. - Some ideas (e.g. how to smartly arrange the graph) were suggestions o1 came up with on its own. It was often worth specifying the requirements more on the "why" and less on the "how", giving the AI the freedom to propose solutions I might not have considered. - More complex requirements were sometimes ignored for a while when they were just part of the "user stories" comment block at the top of the HTML file. Only after explicitly pointing out that they weren’t implemented did the AI make an effort to address them. In summary, I’m excited to continue exploring this development approach over the coming years to see if increasingly complex applications can be built iteratively in this way.
Does the same job
all alternatives →
- OSOur startup Construct 2, how far we've come and lessons learnt so far2012 · ▲12
We did a "Show HN post" 6 months back of our startup and we're very excited to show everyone how far we've come as well as the lessons we've learnt so far! It's been a roller-coaster so far and we think there's lot more of the same to come! We did apply for Ycombinator funding but got turned down :( But may re-apply soon :) For those that don't know, our startup is called Scirra and we make Construct 2 which is an HTML5 game engine (http://www.scirra.com). Our engine allows anyone to make HTML5 games without knowing any programming. It's only me and my brother working on this and we're based…
- 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…
AI-generated music box version of any song (for baby)19d ago · lullabyconverter.com · ▲5title basically covers it. project #2 from my paternity leave. My partner & I got frustrated with hearing Brahm's Lullaby and Wheels On The Bus repeatedly. I also stand by that babies can enjoy adult music just as easily as they can enjoy "kids music". But most adult music is too dense/complex for babies to understand, so I created this to generate baby-friendly, slowed down versions of songs that we like to play for our baby & sing along with. Uses BS-roformer for stemming out the input audio + spotify Basic Pitch for transposing to midi. Still needs some work, kinda sounds like a…
- NJNext.js AI Chatbot Template by Vercel Labs2023 · chat.vercel.ai · ▲6
Hey y'all! Jared Palmer here... Me, @shadcn, and @shuding_ just an open-sourced a new Next.js AI chatbot app template built with Next.js, the Vercel AI SDK, and Vercel KV. Source Code: https://github.com/vercel-labs/ai-chatbot
- THTree-hugger-JS: CSS selectors for JavaScript AST analysis and MCP2025 · ▲7
I built a library that lets you find code patterns using familiar CSS-like selectors, then connected it to Claude via MCP so AI assistants can understand and refactor codebases. The Approach // Find code patterns with intuitive selectors: const asyncFunctions = tree.findAll('function[async]'); const todoComments = tree.findAll('comment[text="TODO"]'); const reactHooks = tree.hooks(); // Built-in React support // Chain smart transformations: tree.transform() .rename('oldFunction', 'newFunction') .removeUnusedImports() .toString(); Key Features - CSS-like…
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 · 26d ago · cactuscompute.com
