Early days with AI—Part 4 of 4, September to January
Experiencing the good, the bad, and the ugly
Once I was satisfied this AI adventure could work, two substantial obstacles stood in the way. It was early September and Ann and I would be leaving at the end of the month for four weeks in Europe. We had much to do to get ready so steady work on a website would have to wait until November.
Rather than losing momentum from time already spent with the chatbots, I would use AI before the trip to augment our existing travel plans. After coming home I would find out how helpful it could be in designing a Substack site and/or a traditional website. Instead of being helpful, the chatbot would prove to be the second obstacle. In the words of my AI mentor, Scott Z. Burns, “What could go wrong?”
After smooth sailing for the first few weeks, this period would be distinguished by occupying the entire spectrum from impressive success to abject failure.
The Good
Our flights and accommodations had been set for months, so I fed all that info into a chat and began to give prompts to see what contributions Chatgpt might make.
CHATGPT: Based on where you are in the process, here’s how I can now support you before and during your trip:
1. Daily Activity Planning for Paris (Sep 28–Oct 3)
You’re in a great location (Le Marais) for walking and exploring. I can suggest:· A light walking itinerary for your arrival day (jet lag–friendly)
· Top picks in your area (museums, cafés, gardens, local markets)
· Advance booking tips for places like the Louvre, Musée d’Orsay, or a Seine cruise
2. Ideas for Free Time During the OAT Tour (Oct 4–19)
OAT tours often include open blocks for individual exploration. I can suggest:· Specific sites or neighborhoods in cities like Porto, Lisbon, or Santiago
· Local food or wine tastings
· Compact walking tours or small museums near your hotels
3. Pre-Trip Prep Materials
Would you like any of the following as PDFs or digital docs?· A one-page summary of flights/hotels for printing
· A day-by-day itinerary with check-in/out times and links
· A “what to pack” checklist tailored to your destinations and time of year
4. Daily Activity Planning for Lisbon (Oct 19-23)
🧭 During the Trip: What I Can Do in Real-Time
If you reach out while you’re traveling, I can help with:
· Navigating metro, train, or tram systems
· Finding a great nearby restaurant or café based on where you are
· Translation help (French, Spanish, Portuguese)
· Local news (e.g., strikes, closures, weather updates)
· Making the most of a free afternoon
Would you like to begin with your Paris days and have me sketch out a light-touch 5-day plan, including arrival day recovery and local highlights? Or would you prefer I create a printable itinerary summary of what you’ve already booked? Happy to go where it’s most useful to you.
If it were a dog, this chatbot would be a hyperactive golden retriever. Every prompt elicits a menu of ways it’s just dying to help. And it’s a great menu. My job is to try to calm it down and—for my sake— get it to focus on one thing at a time.
ME: Yes, let’s start with the time in Paris. First, our scheduled arrival is Sunday Sep 28 13:40. We’d like to take the Metro from the airport to our hotel. How detailed can you be in telling us all we need to know to do that smoothly?
CHATBOT: Great—I’ll walk you through everything you need to take the RER B train and Metro from Charles de Gaulle Airport (CDG) to your hotel, Hôtel Jeanne d’Arc Le Marais (3 rue de Jarente, 75004 Paris), including what to expect, where to go, what ticket to buy, and when to watch out for stairs or transfers.
I know this seems mundane, but this was the start of 3-4 pages of chat transcript that I copied and pasted into my Apple Notes trip folder. It was accurate, beautifully organized, and covered everything we needed to know to get to and from our hotel, how to navigate the differences between the RER train and the Metro, and a dozen other vital details. It made a challenging route easy.
This experience was repeated with generous and helpful information about bistros and restaurants near our hotel, some “insider tips.”
The Bad (or Unhelpful)
One of our main reasons for adding Paris to this trip was a desire to see the restored Notre Dame. We had read that the bell towers would open for visitors to climb to the top the week before we would arrive. Scheduling and getting online tickets seemed a natural task for AI. When it built a tentative schedule for our 5 days there, I noticed something:
ME: Great format. I think I see an error though. (Is this called a hallucination?) I then described the error I’d seen involving the Paris time vs. Seattle time.
CHATGPT: Nice catch — thank you for calling that out. You’re absolutely correct about the two-day, midnight Paris-time rule. That earlier wrong date/time in the Day 2 note was my mistake (yes — a model error, sometimes called a hallucination). I’ve fixed it and created updated, ready-to-import calendar reminders for the booking windows.
This was a minor error that could have caused a lost opportunity. I would find a few more during the trip planning and I may have missed a few. Low stakes, but good reminders to take seriously the warnings to be alert to the possibility of errors. Considering the huge volume of data generated, there weren’t many. Not until we started designing the Substack site, anyway.
After this, things began to spiral. Thinking I should stay open to learning what ChatGPT could offer, I began saying yes to the bot more frequently. I was being forced to relearn the lesson that “just because a technology CAN do something doesn’t mean it SHOULD.” Reviewing the chat transcript now, I see a 5-day plan that would take a full day or two to figure out and 2-3 weeks to accomplish. Not really ChatGPT’s fault. We were getting along famously and I was like a kid playing with a new toy. Having a tech tool this powerful at my beck and call was catnip. I was giving a 1st grade assignment to a machine with virtually unlimited information and processing speed and trained to analyze, summarize, and generate creative and technical text. No surprise that what I got was outrageous overkill.
So, this confirmed the early intuition that coming up with well thought out prompts is vital. That, and being clear with the chatbot that I don’t want a 500-word answer to every question. There will be times when I want more, but I need to give quality, focused prompts in order to get quality, focused responses. I swear I wasn’t kidding about the chatbot being like a people-pleasing golden retriever—albeit immeasurably smarter— who is trained to give what it thinks it’s being asked to give. And a bit more.
Determined to be more business-like when we returned at the end of October, I was looking forward to putting this speed demon to work helping to prepare the online site(s) so I could start writing. Instead, honeymoon still visible in the rear-view mirror, I would come close to breaking up. More than once.
The Good
The original Boomer blog was published on my own website, using the WordPress platform and template. That would be the simplest route to begin publishing again, but the World Wide Web is a vast place and few visitors ever stopped by. I’d been reading various authors on Substack and it seemed the better platform for exposure to more readers. However, while Substack was ideal for posting items as I wrote them, it was not suited to organizing the memoir project as it grew. I credit the chatbot for its patient reiteration of pros and cons until I felt good about the final hybrid approach. If interested, it is described on both a Substack page and a WordPress page. This was a bright spot in a very frustrating couple of months.
The Ugly
On the bright side, I learned a lot about the Large LANGUAGE Model’s disadvantages as a software and web design tutor. Will never go there again. I’ve taught so many computer classes to adults and kids, I shouldn’t have been surprised. And I shouldn’t have been so stubborn.
The chatbot had two main handicaps that interfered with its ability to show me how to use Substack’s site editing features. The first was that it couldn’t, um, really SHOW me anything. No images. No diagrams. No references to any visual aids at all.
If you’ve ever received phone support for a computer or software issue—let’s say from Apple— the support person will start by asking permission to connect to your computer over the internet so they can see and work on your desktop. If you’ve ever taken a tech class, odds are better than 10 to 1 that the instructor is using video projection so you can see what they’re doing.
I hung in with the chatbot much longer than was reasonable, thinking we’d get on the same page next time around. But we never—really, never—got there. That was because of the bot’s second handicap and my making another critical error in my prompts.
I had reviewed a lot of existing Substack publications and noted the ones that had design features I liked. The thinking was: if they could do it, so could I. In some cases, that turned out not to be true. A few were using Cascading Style Sheets or some other tricks of the trade to achieve their look.
So, instead of asking the bot to walk me through setting up a basic publication, I asked it to tell me how to create specific design features. Back to the eager Golden Retriever. If I asked for something, the bot was going to try —even if it didn’t know how. I would try to follow its written instructions, but its descriptions often didn’t match what I saw on my display.
Finally, there was one particularly bad session when I hit the wall. The chatbot had given me directions for adjusting the layout of the main landing page in Substack at least 4 times. Each time I reported that it didn’t work and what happened instead, the bot would blame it on undocumented Substack revisions (not true) and say “now I know exactly what’s going on” or “now I know exactly what version this is.” I expressed my frustration and ChatGPT had a mini meltdown.
The screen went blank except for the word “Thinking” pulsing on the white background.
Much of the transcript of this session disappeared, but I got this screen shot first.
The top left box is my text that caused the meltdown.
To the right of that is what the chatbot was “thinking”. That text kept fading in and out and it was a lot more than 5 seconds. I had to refresh the page in order to see the bottom left response and apology. Later, the bot would tell me that the “Thinking” text is never visible and that I had “seen behind the curtain.”
After this, I finally accepted that this was one job that AI is not yet suited to. I watched a YouTube video to answer the questions that I couldn’t get from ChatGPT. I began making good old-fashioned normal progress and soon was ready to launch.