I made a non-trivial iOS app with GPT-4 in just a few hours
After being inspired by your responses to the Ask HN thread yesterday (https://news.ycombinator.com/item?id=35299071), I decided to see if I could use ChatGPT to make a functioning app. I picked a random project idea out of my Notebook of Amazing Ideas, and spent just a couple of hours using GPT-4 to build it. I've never built an iOS app before, and even if I made something like this as a web app (my usual job), I would expect it to take at least a week. My process was basically 1) Ask ChatGPT to write some code 2) Copy and paste the code into the right files (this took a…
In plain words
This is a demonstration of using GPT-4 to rapidly develop an iOS application. A developer with no prior iOS experience built a functioning app in a few hours by having the AI generate code, then iteratively fixing errors through back-and-forth prompting. The process involved copying generated code into appropriate files, running the application, and feeding error messages back to GPT-4 for solutions. The project illustrates how AI coding assistance can significantly compress development timelines for developers experienced in other frameworks like web development.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
After being inspired by your responses to the Ask HN thread yesterday (https://news.ycombinator.com/item?id=35299071), I decided to see if I could use ChatGPT to make a functioning app. I picked a random project idea out of my Notebook of Amazing Ideas, and spent just a couple of hours using GPT-4 to build it. I've never built an iOS app before, and even if I made something like this as a web app (my usual job), I would expect it to take at least a week. My process was basically 1) Ask ChatGPT to write some code 2) Copy and paste the code into the right files (this took a little bit of React knowledge on my part). 3) Run the code and paste any errors back to ChatGPT and ask it for suggested solutions. 4) Repeat.
Does the same job
all alternatives →
- BGBuild GPT-powered apps with just GPT4 prompting2023 · picoapps.xyz · ▲22
Hi everyone, We built a quick experiment this weekend that allows you to use GPT4 to quickly generate shareable web apps that use the ChatGPT API. Here’s a video of me building an app similar to https://whatdoesthiscodedo.com/: https://www.youtube.com/watch?v=VpvGd21V0u0 "What does this code do?" went to #1 on Hacker News a couple of months ago. The app takes a piece of code, asks GPT4 to analyze it and returns a simple, English description of the code. An app like this is super simple to build with MetaGPT. What other kinds of things can you build with this? *…
- WGWhole Git repo was made with ChatGPT2022 · github.com · ▲231
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, March 2023
the whole month →
- BI
I'm a big fan of the BBC podcast In Our Time -- and (like most people) I've been playing with the OpenAI APIs. In Our Time has almost 1,000 episodes on everything from Cleopatra to the evolution of teeth to plasma physics, all still available, so it's my starting point to learn about most topics. But it's not well organised. So here are the episodes sorted by library code. It's fun to explore. Web scraping is usually pretty tedious, but I found that I could send the minimised HTML to GPT-3 and get (almost) perfect JSON back: the prompt includes the Typescript definition. At the same time I…
AI · 2023 · genmon.github.io