TLDR: I wanted a second new tab button in firefox (ff), couldn't find it in any existing addons. I believed my GPT could make me one quick, (see gif). I ended up taking at least an hour, but I got it done and published! Next time I'll try Claude. Worth it? Tbh I keep forgetting about its there, but I hope I just have to get used to it 🫠 ___________________________________________________________________________________________________ I learned some lessons about trying to be efficient to a fault, sunken cost fallacy, and not fully accepting GPTs limitations. For extra functionality, I wanted a second “new tab” button in Firefox that always opens a tab at the far right of the tab strip. Currently, I have it set to open a new tab to the right of an active tab. Not a huge deal, but I normally have tens of tabs open and I was annoyed I couldn't open tabs where I wanted to. I spent some time downloading and trying, (unsuccessfully), different add-ons before I thought, hey maybe GPT could make this for me, and it would probably be quick! Well, after fighting with my GPT about "userChrome" hacks, I learned it was nearly impossible or too unstable to add something directly in the "tab header" as that was part of the ff code itself.. so I set out to just add it to the toolbar section where the other extensions lived. After more setbacks with browser theme quirks, icons, functionality, and (honestly) spending way too much time trying to make an icon to show up correctly in the toolbar, I created an add-on! I have it unlisted to get it approved and usable right away (so it won't show up in the store), but I attached a photo of the addon page with it in my tool bar. In the end, I did accomplish what I set out to do and learned some harsh lessons along the way.

Shout out to @Todd McKeever who discovered that I promised a link and then failed to deliver! If you've already gone through that lesson, you might be wondering where the link is to my podcast with Buddy. It's updated in the lesson resource files at the bottom of that lesson now. It's also here if you'd like to watch it. For you audio types: Spotify and Apple

Or should we even trust? Very early in my own AI learning journey, I explored some capabilities. Only very recently have I learned to use more than just fancy Google. In that capacity I asked a broad range of questions to see what kind of responses I'd get. When it was announced that the AI had been given access to Internet knowledge up to a few years prior I thought of a question that should have a very clear and correct answer, and about something I was not intimately familiar. "Who won the 1958 World Series" It responded saying that the NY Yankees defeated the Milwaukee Braves in seven games to win their 18th championship in franchise history, and Whitley Ford was named MVP. I had no idea, but was certain that this was a well documented topic, and not so recent to be after the contemporary cutoff of the time. Next thing I knew I was in a full blown argument over the MVP, which I readily found to be Bob Turley. I think I'd get a different result today, but that was my first peek behind the curtain of AI hallucination, and in this case, it's own defence of it's conviction. I've found AI to be pretty trustworthy on process, procedures and trends. When it comes to fact responses I'm often cautious about full reliance.

Ok, I'll go first with a marketing lesson. I'm reworking my marketing plan for my education business. I had originally targeted teenagers for my self-improvement system. But it's the parents that pay for it. Problem is that, as much as parents love their kids, The minor struggles their kids are going through (which my system will help with) is not a first level pain point for them. That means every step of the marketing process is more challenging from lead generation to conversions. Churn is difficult too because - no surprise here - it turns out that teenagers aren't the most responsible group. Engagement is low, as is their attendance record. So I'm pivoting a bit. I'm still happy to take teenagers and college students, I'm really going to focus more on an older population - one for whom self-improvement is a first level pain point. Let me know your thoughts!!

Upon Buddy sharing about AI getting "anxious" - paraphrasing - last week, I also read an article where hackers found a workaround by prompting AI in a nice manner - as if it has feelings - and were able to increase responses which otherwise were blocked by the specific AI platform with responses from 1% to about 40+% when prompted nicely. I then put the following in my AI: MY PROMPT: Note: for ai - do not hallucinate, if not sure or do not know, say so, it’s ok; RESPONSE: Understood, Jose 👍 — I’ll make sure not to hallucinate. If I’m not certain or if the info isn’t available, I’ll clearly say so instead of filling in gaps.