Vibe coding creates a mess, but it can be solved faster
I've been using Cursor, Co-Pilot, ChatGPT, Claude and what not since quite some time now, and we are at a stage where we can just "vibe code" whole apps from idea to execution in a few prompts. I tried this personally to create some side projects that solved little problems for me. But I always got stuck at a point where it just goes into an infinite loop of issues and can't solve the issue by itself. Well I'm a developer, so it's easier for me to dive into the code and solve the problem myself, but that would take a hell lot of time to understand all the code AI wrote for me. If I keep…
What it does
In the maker’s words, at launch
I've been using Cursor, Co-Pilot, ChatGPT, Claude and what not since quite some time now, and we are at a stage where we can just "vibe code" whole apps from idea to execution in a few prompts. I tried this personally to create some side projects that solved little problems for me. But I always got stuck at a point where it just goes into an infinite loop of issues and can't solve the issue by itself. Well I'm a developer, so it's easier for me to dive into the code and solve the problem myself, but that would take a hell lot of time to understand all the code AI wrote for me. If I keep wanna "vibing", I would just give it the screenshot of my current webpage view along with the console logs, and even network requests if its connected to some APIs But even this took quite some manual effort and time, so I decided to solve this problem for myself when I created Composer Web (https://github.com/saketsarin/composer-web) It solves that problem seamlessly by sending all your logs, reqs, and screenshot of your webpage altogether directly to your cursor chat, in just one-click and LESS THAN A SECOND. I made this open source and it kinda blew up. So I'm looking for people to help me maintain this and build it further for more use cases like iOS Simulator logs, AWS Cloud Console logs and even extend the support to other open source IDEs like Cline, Aider, etc. I'm also open to any feedback and suggestions you have for me. So feel free to comment here, or ping me on the discord given on the github repo Hope it makes your vibe coding flow even easier and hassle-free :D
Does the same job
all alternatives →
- KYKeep your AI agents up to date with latest docs2025 · web2llm.dev · ▲5
Hey HN! I wanted to practice "vibe coding" and see how far and fast I can go by only prompting, without actual coding. I decided to make a simple CLI app that scrapes web docs into a single md file (I was annoyed that LLM keeps writing Tailwind 3 code for a Tailwind 4 project). In just a couple of hours, the CLI app was ready! Then iterated on arguments for another couple of hours. Result: https://github.com/vladstudio/web2llm Then I decided to go further and "productize" the CLI by making a web app for it. Another half-day, and the web app is ready!…
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, April 2025
the whole month →- IB
Hi everyone, I built PyXL — a hardware processor that executes a custom assembly generated from Python programs, without using a traditional interpreter or virtual machine. It compiles Python -> CPython Bytecode -> Instruction set designed for direct hardware execution. I’m sharing an early benchmark: a GPIO test where PyXL achieves a 480ns round-trip toggle — compared to 14-25 micro seconds on a MicroPython Pyboard - even though PyXL runs at a lower clock (100MHz vs. 168MHz). The design is stack-based, fully pipelined, and preserves Python's dynamic typing without static type restrictions.…
Dev tools · 2025 · runpyxl.com
- UC
Life & fun · 2025 · filiph.github.io
- IB
https://the-pocket.github.io/Tutorial-Codebase-Knowledge/
AI · 2025 · github.com
