How I Used ChatGPT Over A Long Weekend

When I tell people how great ChatGPT is (or substitute your favorite AI tool like Claude), the question I hear most often is: “But how do you actually use it?” It’s a great question because, as I explained in this blog post, working with large language models (LLMs) isn’t always intuitive and takes some practice to master.

Rather than scrambling to come up with examples on the spot, I decided to document how I used ChatGPT over a four day weekend. While this list isn’t exhaustive or representative of every weekend, it’s a great starting point for anyone curious about what ChatGPT can do.

You don’t have to read through every single use case, you may want to skim the post and dive into the ones that strike your fancy. If you aren’t a developer, by all means, skip the coding section. If you don’t need health advice, then scroll past how I’ve used ChatGPT to diagnose my medical issues. There is a wide array of use cases discussed, and I’m sure at least one of these AI-assisted workflows can improve your life.

Coding

Solving multiple complex coding challenges

You’ll see the full results in Boutique 3.0, but I was thrilled with how ChatGPT’s o1 model helped me brainstorm, prototype, and build a feature inspired by Swift Data’s Relationships. This feature has been on my wish list for over a year, but I kept putting it off because of the complexity.

Using ChatGPT as a pairing partner, I developed about 10 potential APIs for this feature in under an hour, and ultimately found one that I loved. ChatGPT then built a first version of the implementation, which got me 90% of the way there, requiring only minimal tweaks to fully align with my goals and preferences.

I also turned to ChatGPT as a teaching aid to review and understand this pull request. This was a fix for a long-standing bug in Boutique, but I had a bit of a mental block when trying to understand how it resolved the issue. I asked ChatGPT to double-check my assumptions and explain what I was missing. Being a software developer is as much about understanding code as writing it, and having a tool to improve my comprehension has been invaluable.

Building a simple app

I've been dealing with a prolonged bout of tinnitus, and the only thing that seems to help is listening to specific nature sounds — like a mix of fire crackling and light rain. Unfortunately, the app I was using for this was buggy and frustrating to navigate. I realized I could build a better app in just 20-30 minutes with ChatGPT. So, I extracted the sounds from the app’s IPA file and let ChatGPT help me create a new, more functional app with a better interface. Did I absolutely need to build this? No. But it’s made my life a little easier during a tough time.

Sidenote: This is a perfect example of how software development is changing. The marginal cost of creating software has always been high, but with LLMs and the tools being built around them, it’s only getting lower. Developers should take note. Making bespoke apps on demand is already possible — and this kind of capability will continue to shape the future of the industry.

Writing SQL queries for me

I often need to analyze how people are using my app, Plinky, to better understand how I can build a product that truly helps them. To make informed, data-driven decisions, I needed to determine the ideal number of links users can save before encountering a paywall.

To find the right number, I decided to look at the average and median number of links users save in their first day, first week, and first month. Writing queries for this type of analysis can be tedious, especially with complex database schemas.

By providing ChatGPT with my database’s DDL (Data Definition Language), I gave it an accurate understanding of my database’s structure — without sharing any actual data. With that context, ChatGPT generated a useful SQL query in seconds, providing the insights I needed. What normally involves googling SQL syntax and some trial and error was effortless with ChatGPT.

Automating tedious tasks

Fixing annoyances with one-off Python scripts

There are small tasks that annoy the heck out of me, but these days, I often ask ChatGPT to write a script to do them for me. The last script I generated was a command line tool that allows me to pass in a list of simulators I would like to keep available in Xcode, and then have simctl delete all the other simulators for me.

This saved me time and hassle. Instead of scrolling through an endless list of unused simulators in Xcode (which get re-added after every update), I was able to quickly fix the problem without spending much time figuring out how to write the script myself. ChatGPT’s ability to generate functional code to solve tedious problems is something I’ll never get enough of.

Transforming colors in a color palette

While considering new color schemes for Plinky, I wanted to quickly prototype colors without having to spend too much time building out a full color palette. Below is the prompt I used to make this work.

I have four different shades of purple colors.

• Light Mode Normal Contrast: #8E44AD

• Dark Mode Normal Contrast: #9B59B6

• Light Mode High Contrast: #AD68C9

• Dark Mode High Contrast: #783A91

I'm trying to replace this color in my color palette with a new shade of blue. The color is #8ECAE6, and I would like to use that for the Light Mode Normal Contrast option. Can you create the other three colors applying the same transformations that we used for our shades of purple?

ChatGPT delivered exactly what I needed: four perfectly tinted shades of blue — #8ECAE6, #9BDFEF, #ADEEFF, #78C0CA — each with slight offsets applied for the respective color modes. It was much faster than if I had attempted to create a whole palette myself, which is important because now I was able to try out a bunch of color schemes and see if any of them fit my needs.

Double-checking my work

Verifying work I’ve done

As a small business owner, I file quarterly taxes, well, every quarter. It’s a tedious task, and the cost of making a mistake is high. Nowadays, after copying data between spreadsheets as I usually do, I paste both the original and updated spreadsheets into ChatGPT and ask it to compare them.

While I can’t guarantee ChatGPT catches everything, this highlights any differences or potential errors I might have missed. It has found mistakes before, and while I can’t guarantee it will always help, it’s still better than nothing. This quick check has become an important part of my workflow, giving me a little boost of confidence that I’m getting things right.

Writing better copy

I like to think I’m a pretty good writer, but I often struggle with microcopy. My penchant for illustrative language doesn’t translate very well to the concise, clear text needed in my apps — especially when it’s crucial to communicate information to users quickly.

This is where ChatGPT has been a huge help. I’ll upload a screenshot of a screen I’ve built with my best attempt at writing good copy, and ask how I can make the copy more concise and direct. It was particularly useful during my recent redesign of Plinky’s onboarding messages. With ChatGPT’s suggestions, I’ve been able to fine-tune the language across my app and deliver a better experience for users.

Research

Music Discovery

I have a pretty eclectic musical palate, and I’m always looking for new music to listen to. Apple Music and Spotify give you access to every artist, album, and song imaginable, but when I find something I like, what I want is more of that. Unfortunately, their discovery features aren’t great — you either browse endlessly or let an algorithm recommend music until something catches your ear.

This weekend, I was listening to Chad Hugo, and all I could think was, “Damn, this slaps.” I ended up having a whole conversation with ChatGPT about him, asking about who he’s worked with, his musical influences, and for more interesting things I should know about him. Then I asked: “Name five other artists I should check out if I like Chad Hugo.”

ChatGPT suggested Pharrell, Daft Punk, Timbaland, The Chemical Brothers, and Mark Ronson. I’ve listened to a bunch of music by three of those artists, and agreed they were spot-on for my taste. That gave me confidence to check out the other two, and led me to discover a bunch of new music I’m now excited to listen to.

Identifying a bird on my fire escape

My lil cat loves watching birds, and while she’s not the most successful hunter (the window hurts), she remains fascinated and convinced she’ll get them one day. I noticed a bird on my fire escape that definitely wasn't a pigeon, and was curious about what bird had such a beautiful speckled chest. With just one photo ChatGPT was able to correctly identify the bird as a European Starling, which it turns out is a lot more common in New York City than I expected.

Note: I did a Google Image search to confirm that the bird was indeed a European Starling, but wouldn’t have known where to start if I hadn’t asked ChatGPT in the first place.

Answering menu questions

I was out at a restaurant, and the menu contained a handful of items I was unfamiliar with. I wanted to find out what they were and if they sounded good, so while I could have googled each item individually, instead I took a picture of the menu and asked ChatGPT about three dishes at once.

Asking about the causes of poor coordination

I was walking down the street when I had a random thought: what causes some people to have poor coordination? I decided to ask ChatGPT:

What causes a person to have poor coordination? Is it usually neurological, biomechanical, or something else entirely?”

The response was very insightful and sparked even more questions. ChatGPT explained various causes, including neurological issues, muscle imbalances, and even inner-ear problems. Each answer led to new questions, and before I knew it, I’d spent 10 minutes learning how about coordination works. ChatGPT turned a stray thought into an impromptu lesson — one of the things I truly love about using it.

Planning a few days in Colombia for an upcoming vacation

This is probably the most relatable item on the list. My wife and I are planning a vacation to Cartagena, and we didn’t know that much about the city. We wanted a trip that matched our vibe — something we’d enjoy by mixing together some highlights, beach time, and some off-the-beaten-path recommendations.

Using ChatGPT’s suggestions as a starting point, we put together a great itinerary in half the time it would normally take us. While I wouldn’t suggest planning an entire trip around ChatGPT’s recommendations, it’s an excellent tool for gathering ideas and must-see attractions quickly. Being able to combine popular spots with hidden gems made vacation planning much easier and more enjoyable.

Learning about Thomas Hardy

I started listening to an episode of Conversations with Tyler featuring Paula Byrne, a biographer who recently wrote a book about Thomas Hardy. While the conversation seemed fascinating, I realized I didn’t know nearly enough about Thomas Hardy to follow along well.

Rather than giving up on the episode, I provided ChatGPT a transcript of the episode and asked:

Can you read the transcript of this podcast, and teach me everything I would need to know about Thomas Hardy to understand what is being discussed?

ChatGPT gave me a comprehensive overview of Hardy’s life, works, and themes, which provided the context I needed to enjoy the rest of the episode. This was the first time I'd tried an idea like this, and it's a technique I'll definitely use again to learn about unfamiliar subjects.

Understanding the home loan process

My wife and I are looking into buying our first home, and to be honest, we don’t know much about where to start. There are so many steps and possible optimizations — it’s the kind of problem I’d normally love to develop expertise in, but I don’t have the time to explore right now. ChatGPT is great at breaking down big problems into simpler ones, so we decided to start there.

ChatGPT gave us a concise list that explained what financing options might be available to us, what paperwork we’d need, and a myriad of other steps involved. The best part was ChatGPT’s ability to answer follow-up questions when we didn’t fully understand certain steps, or advice we’d been given. By the end of the weekend, we felt much more confident and even scheduled a call with our bank. We’re still far from experts, but being able to ask questions and get thorough answers made the process far less intimidating.

Re-thinking my investment portfolio

With the end of the year approaching, I’ve had taxes and finances on my mind. I had a little money to invest, and while I’ve historically been pretty conservative, I wanted to explore other options. I knew I wanted to stick with index funds, but instead of defaulting to the same ones I usually choose, I asked ChatGPT for suggestions.

After sharing my goals for a slightly more aggressive portfolio, ChatGPT provided a list of potential mutual funds and ETFs to consider. From there, I did my own research, narrowed it down to three, and then asked ChatGPT to compare their performance over the last 1, 5, and 10 years. This helped me make a more informed decision in less time than it would have taken to manually search and analyze the data. ChatGPT didn’t replace my judgment, especially for something this important — it just made the process faster and more efficient.

Holiday shopping inspiration

I put a lot of thought and care into the gifts I give, especially for the closest people in my life. But sometimes, you need to find a gift for someone you don’t know well enough to find that perfect present. In one instance, I gave ChatGPT the details I knew about this kind of person and asked it to generate 25 gift ideas they might like.

Ethan Mollick wrote a great post about how ChatGPT is infinitely patient, so you might as well ask it to generate a whole bunch of ideas at once, knowing that some will inevitably be misses. Out of the 25 suggestions, I found five solid options and chose one that would make most people happy — which is really the goal when you’re buying a gift for someone you don’t know well, like at a company holiday party.

Health

Finding a temporary solution for my tinnitus

After six flights in 10 days this past September, I began struggling with tinnitus. None of the doctors I consulted could offer a clear explanation, and some even suggested it was hearing loss despite my perfect audiograms. I suspected Eustachian Tube Dysfunction (ETD), though all but one dismissed the idea. Using ChatGPT, I was able to narrow the issue down to ETD, likely exacerbated by dry nasal passages.

By bouncing ideas off ChatGPT and asking targeted questions, I found a temporary solution: using a saline mist spray to keep my nose hydrated. This has helped alleviate the symptoms while I waited to see a specialist. Without ChatGPT, I likely wouldn’t have connected the dots and found the relief I needed for now.

Medical research and differential diagnosis

I’ve been dealing with severe nerve pain for over three years, and while I could write pages about the struggle, I’ll save that for another time. What’s important is that I’ve seen more than 50 doctors, and only two have truly helped me make progress. Frustrated with the lack of answers, about six months ago I started turning to ChatGPT and Claude as a diagnostic partner — and it has made a meaningful difference.

By asking ChatGPT targeted questions about my symptoms and experiences, I’ve been able to better understand the biology of my body, and developed more informed ideas to discuss with my doctors. Thanks to this approach, I’ve identified and treated two nerve issues (one rare and one uncommon) that were causing my pain. I now have a theory for the one remaining problem (🤞🏻), and all that's left is an MRI of my thoracic spine to confirm. (That, and because I live in America, convincing my insurance company to approve the scan...)

ChatGPT hasn’t replaced my doctors, nor do I expect it to anytime soon. What it has done is give me more knowledge and allowed me to test theories that I can bring to my doctors. This is critically important in a medical system where a doctor may only spend 5-10 minutes with you, now I’m able to make the most of that limited time. While the process is far from perfect (and endlessly exhausting if I’m being honest), I’m working with my doctors and within the system’s rules. AI has been a powerful ally throughout this journey.

Modifying my Pilates routine to accommodate for pain

This was probably the hardest item on the list to google. I have a Pilates routine that I do 5-7 times a week to keep my core stable and take strain off the nerves in my torso. While the routine has worked well for years, I needed to temporarily adjust it to accommodate a new pain in my shoulder blade.

To make this change, I shared a screenshot of my pilates routine from the Peloton app with ChatGPT, explained my specific pain points, and asked it to modify the exercises to include bands while keeping me off my back more. The result was an updated routine that fit my needs perfectly — a task I’m not sure how I could have done without without ChatGPT.

Editing this blog post

As someone who takes a lot of pride in my writing and deeply cares about word choice, I will always be transparent about how I use AI to edit my work. I rely on a detailed prompt, part of which reads: “I want the edits to be focused on making the post more concise and to the point, but I do not wish to change the writing style in a way that will make it sound like another person wrote it. The writing should always maintain my tone, sense, and sensibilities.”

I wrote the first draft of this post and refined it myself. ChatGPT’s value in this process was primarily in formatting and structure — I originally wrote this as a series of bullet points. After that I used ChatGPT to discuss ideas about how to clarify my points, which helped me shape the second draft.

This is a collaborative process, thanks to another part of my prompt, which states: “We will edit this post together paragraph by paragraph, rather than all at once.” This interactive approach allows me to go back and forth with ChatGPT, rather than relying on it to do the work for me. Not only does this improve my writing, but it also helps me grow as a writer as I reflect on the many implicit and explicit suggestions ChatGPT offers.

That said, I don’t always use AI for my writing. For example, I write about 1,000 words a day in my journal without any AI assistance because I want every letter of those words to be completely my own. But I have to admit, having a partner to proofread and refine my blog posts has made it easier to publish more frequently. Posts like this would likely take too much effort to share without AI, which makes me think despite people using ChatGPT to create AI slop, there’s significant value to be derived from AI editing in the future.

---

I actually used ChatGPT much more this weekend, but I left out simple Google-style queries and redundant use cases, such as a swath of additional health questions I’ve explored. If you asked me how I used ChatGPT on another weekend, the list would be different but would likely have a lot of overlap in style and purpose.

What I wanted to illustrate was that with AI, we’ve been given the gift of the world’s smartest and most patient collaborator. AI is such an empowering tool, and how you choose to use it is entirely up to you — but I would urge you not to pass up this golden opportunity.