What a designer can ship with GPT in 8 days
After getting impatient with a "SwiftUI for Designers" course I decided to fuck around and find out. Just hours after asking my 1st question: "Are you familiar with SwiftUI?" the core functionality of this app (an exercise utility) was up and working. I've spent the past week tweaking the UI with small animations and features. It's a humble tool (local storage only) but I am nonetheless floored with how GPT has allowed me to completely skip the "learning syntax" part of development and ship something that I actually use. Not only did it lower the syntax bar virtually to 0... I've learned…
In plain words
An exercise utility app built with SwiftUI and developed in eight days with GPT assistance. The tool features local storage, animations, and UI refinements created by a designer with minimal Swift experience. It demonstrates how AI can accelerate app development by eliminating the need to learn syntax fundamentals, allowing a creator to move directly from concept to a functional, usable product.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
After getting impatient with a "SwiftUI for Designers" course I decided to fuck around and find out. Just hours after asking my 1st question: "Are you familiar with SwiftUI?" the core functionality of this app (an exercise utility) was up and working. I've spent the past week tweaking the UI with small animations and features. It's a humble tool (local storage only) but I am nonetheless floored with how GPT has allowed me to completely skip the "learning syntax" part of development and ship something that I actually use. Not only did it lower the syntax bar virtually to 0... I've learned just as much or more syntax from reading and debugging GPT outputs than I would by taking a course. For fairness: I'm a design cofounder and self-taught React Native front-ender with 2 years of total experience in software (0 Swift). I am not a data structures person. After working with ChatGPT to get the file structure and skeleton components set up over the span of ~3 days, I decided to scrap our previous data structure and propose a new one after realizing our first was too brittle to build certain components that I wanted. Below is the prompt which resulted in the current data structure and functionality of the app, which is live on TestFlight for anyones use: ////////// PROMPT ////////// You are a full-stack iOS developer using SwiftUI. Together we are going to write the code for a two-tab exercise app which stores data locally using AppStorage and UserDefaults. The app takes individual exerciseEntries which have a name and a count, and sorts these into groups called exerciseGroups. ExerciseGroups are defined as any set of exerciseEntries which have the same name and occur with no more than 30 minutes between consecutive exerciseEntries. On the first tab of our app, users input each exerciseEntry. On the second tab, they view their historical data. The first tab of the app is already complete, and we now only need to write the logic which occurs when a new exerciseEntry is submitted. When a user submits an exerciseEntry, three arrays stored in AppStorage should simultaneously update with the correct data: Exercises[], which contains an array of all exerciseEntries the user has submitted ExerciseGroups[], which contains an array of all exerciseGroups Days[], which contains an array of days The data model is defined in a separate Swift File called ExerciseDataModel.swift: public var exerciseTypes = ["Push Ups", "Pull Ups", "Chin Ups", "Squats", "Calf Raises"] // ExerciseEntries struct ExerciseEntry: Identifiable { var id = UUID() var exerciseName: String var count: Int var timestamp: Date } // ExerciseGroups struct ExerciseGroup: Identifiable { var id = UUID() var groupName: String var entries: [ExerciseEntry] var startTime: Date var duration: TimeInterval } // ExerciseTotals struct ExerciseTotal: Identifiable { var id = UUID() var exerciseName: String var total: Int var date: Date } // Days struct Day: Identifiable { var id = UUID() var date: Date var exerciseGroups: [ExerciseGroup] var totalCounts: [ExerciseTotal] } Based on this information, can you write a function that correctly updates the data in AppStorage after each time a user submits a new exerciseEntry? I would suggest that this function first updates the Exercises[] array, followed by the ExerciseGroups[] array, and finally the Days[] array based on the logic defined above. ////////// END PROMPT //////////
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, April 2023
the whole month →
- G4
Hi HN, Today we’re launching GPT-4 answers on Phind.com, a developer-focused search engine that uses generative AI to browse the web and answer technical questions, complete with code examples and detailed explanations. Unlike vanilla GPT-4, Phind feeds in relevant websites and technical documentation, reducing the model’s hallucination and keeping it up-to-date. To use it, simply enable the “Expert” toggle before doing a search. GPT-4 is making a night-and-day difference in terms of answer quality. For a question like “How can I RLHF a LLaMa model”, Phind in Expert mode delivers a…
AI · 2023 · phind.com
