A portfolio that re-architects its React DOM based on LLM intent
Hi HN, Added a raw 45-second demo showing the DOM re-architecture in real-time: https://streamable.com/vw133i I got tired of the "Context Problem" with static portfolios—Recruiters want a resume, Founders want a pitch deck, and Engineers want to see architecture. Instead of building three sites, I hooked up my React frontend to Llama-3 (via Groq for <100ms latency). It analyzes natural language intent from the search bar and physically re-architects the Component Tree to prioritize the most relevant modules using Framer Motion. The hardest part was stabilizing the Cumulative…
What it does
In the maker’s words, at launch
Hi HN, Added a raw 45-second demo showing the DOM re-architecture in real-time: https://streamable.com/vw133i I got tired of the "Context Problem" with static portfolios—Recruiters want a resume, Founders want a pitch deck, and Engineers want to see architecture. Instead of building three sites, I hooked up my React frontend to Llama-3 (via Groq for <100ms latency). It analyzes natural language intent from the search bar and physically re-architects the Component Tree to prioritize the most relevant modules using Framer Motion. The hardest part was stabilizing the Cumulative Layout Shift (CLS) during the DOM mutation, but decoupling the layout state from the content state solved it. The Challenge: There is a global CSS override hidden in the search bar. If you guess the 1999 movie reference, it triggers a 1-bit terminal mode. Happy to answer any questions on the Groq implementation or the layout engine!
Does the same job
all alternatives →- AJAffinity.js – A simple view component library with store2018 · ▲33
with affinity you can make multiple apps (components eventually) and store (ala redux) - while a store can be shared through apps. This started as a case study and as a small reusable code for creating self contained dom elements with functionality - during the time of development, ideas and inspiration came from angular, react and vuejs. suggestions and feedback is mostly welcomed. The interesting challenges were finding ways for these topics: 1. create a component lib using dom and js only, without any 3rd party . 2. producing semantic html in dom . 3. allow template micro syntax (using…
- RARemake – A server-rendered framework for building CRUD web apps fast2020 · ▲47
I wanted to have a framework that would let me build web apps faster than ever before. I didn’t care if it was a little hacky or didn’t use best practices — I wanted to be able to get a multi-user application out the door in hours instead of months. I researched the CMS space for months before deciding to build something from scratch. My goal was to be 90% done building a web app once I had the static HTML and CSS finished. I’m not a big fan of building out API endpoints over and over again for every new app, fiddling with a database, or doing lots of config. What I ended up with was a…
- NRNoact – React-like Virtual DOM library in 70 lines of TypeScript2020 · github.com · ▲50
- IMI'm building an AI tool that turns Design Systems into React components2024 · robustlaunch.com · ▲8
Hi HN! Solo developer here. 10 days ago, I started building this after spending countless hours copying/pasting marketing sections and fighting to keep them consistent with our design system. I wondered: "What if AI could understand our design system and generate React components that actually match it?" Current progress (10 days in): - Can generate hero sections that follow your design tokens - Uses your actual component variants and styles - Works with Next.js, Tailwind, shadcn/ui It's very early days, but I'm excited to share it with other devs who: - Are tired of rebuilding…
- RJReact.js LLM Agent (open-source)2023 · github.com · ▲8
I've been working in the couple of months on an experiment, trying to make GPT-4 much more useful for web development / React, writing production code that is relevant to any repository without copy pasta from ChatGPT or having small snippets of auto-complete from Copilot that are not in your context. The agent is taking a user story text and generating and composing multiple react components to generate the relevant screens, based on atomic design principles, with Typescript, TailwindCSS and RadixUI. Is is still experimental but very interesting results, I would like to get your…
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
