An AI that reliably builds full-stack apps by preventing LLM mistakes
Hey HN! Previous CERN physicist turned hacker here. We've developed a way to make AI coding actually work by systematically identifying and fixing places where LLMs typically fail in full-stack development. Today we're launching as Lovable (previously gptengineer.app) since it's such a big change. The problem? AI writing code typically make small mistakes and then get stuck. Those who tried know the frustration. We fixed most of this by mapping out where LLMs fail in full-stack dev and engineering around those pitfalls with prompt chains. Thanks to this, in all comparisons I found with: v0,…
In plain words
Lovable is an AI coding tool that builds full-stack applications by identifying and preventing common LLM mistakes. It maps out where language models typically fail during development and uses prompt chains to work around those pitfalls. The tool is designed for developers who want AI to reliably generate working code without getting stuck on errors. It handles larger codebases and compares favorably to similar AI coding assistants.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! Previous CERN physicist turned hacker here. We've developed a way to make AI coding actually work by systematically identifying and fixing places where LLMs typically fail in full-stack development. Today we're launching as Lovable (previously gptengineer.app) since it's such a big change. The problem? AI writing code typically make small mistakes and then get stuck. Those who tried know the frustration. We fixed most of this by mapping out where LLMs fail in full-stack dev and engineering around those pitfalls with prompt chains. Thanks to this, in all comparisons I found with: v0, replit, bolt etc we are actually winning, often by a wide margin. What we have been working on since my last post (https://news.ycombinator.com/item?id=41380814): > Handling larger codebases. We actually found that using small LLMs works much better than traditional RAG for this. > Infra work to enable instant preview (it spins up dev environments quickly thanks to microVMs and idle pools of machines) > A native integration with Supabase. This enables users to build full-stack apps (complete with auth, db, storage, edge functions) without leaving our editor. Interesting project as an example: https://likeable.lovable.app – a clone of our product, built with our AI. Looks like a perfect copy and works (click "edit with lovable" to get to a recursive editor...) Going forward, we're shipping improvements weekly, focusing on making it faster, even more reliable and adding visual editing experience similar to figma. If you want to try it has a completely free tier for now at lovable.dev Would love your thoughts on where this could go and what you'd want to build with it. And what it means for the future of software engineering...
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
Launched alongside, November 2024
the whole month →
- IB
I wasn't quite sure if this qualified as "Show HN" given you can't really download it and try it out. However, dang said[0]: > If it's hardware or something that's not so easy to try out over the internet, find a different way to show how it actually works—a video, for example, or a detailed post with photos. Hopefully I did that? Additionally, I've put code and a detailed guide for the netboot computer management setup on GitHub: https://github.com/kentonv/lanparty Anyway, if this shouldn't have been Show HN, I apologize! [0]…
Dev tools · 2024 · lanparty.house
