Welcome back
I’m rebuilding my blog, but this time with AI. All I can promise is I will strive to make sure this is worth reading. I started a newsletter and blog during Covid. It was mainly about trading during the meme-stock frenzy. I’m also fascinated by macro economics, so there were some posts about how the economy was reacting to the pandemic. I spent some time with Wordpress and Mailchimp. I really enjoyed the writing and moreso talking with friends about the posts. However, I found the technical and research side of things to be a bit too much like my day job, and when that picked up, I started to burn out. I stopped posting and eventually let the whole thing die.
What I’m trying to do
I’m on parental leave (yay, it’s the greatest!), and I wanted a project to work on that was creative, technical, and social. Over the last 15 years since I started programming, I’ve had countless side projects, none of which ever technically got finished. Most were developed to help me learn something new, or stay fresh on topics I wasn’t focused on at work.
Over the past few years, I’ve been working too much and I haven’t felt like expanding my technical chops. Creative projects seemed too daunting to start, and I never had a clear vision of what I wanted to build. More importantly I didn’t have the ‘why’ behind any project. But now feels different.
Expanding my technical skills is futile with pace of change in AI. My usual conundrum of picking a project is also still a problem since anything I do decide to learn, but lack full conviction, will likely be obsolete in a few months. Even as I type this out, AI-auto-completion is starting to understand where I’m going with this post and it’s taking all my will power to not let it write the whole thing.
So that’s the why: how do I build something that harnesses AI, but still includes a part of my brain that AI cannot (yet) do? There’s no answer, but there is a process.
I can build and deploy a blog in about 10 minutes (I’m already connected to free services that will deploy and I have a domain I can keep using). But that site will certainly not be interesting. Why would anyone go to my ai-generated blog?
So, right now this blog is a journey of me building lots of new things and then evaluating the quality of the output.
What is quality
Whenever I evaluate something - whether if it’s whether I like it, if I can trust it, if it’s worth spending my time or money, I always think about the book The Zen and Art of Motorcycle Maintenance. Here’s a great quote, but there are so many I’d suggest just reading the book:
“Quality…you know what it is, yet you don’t know what it is. But that’s self-contradictory. But some things are better than others, that is, they have more quality. But when you try to say what the quality is, apart from the things that have it, it all goes poof! There’s nothing to talk about. But if you can’t say what Quality is, how do you know what it is, or how do you know that it even exists? If no one knows what it is, then for all practical purposes it doesn’t exist at all. But for all practical purposes it really does exist.”
With this proverbial genie in a bottle that sits at my finger tips, I can effectively ask my Claude to build any project that pops into my head, but in the past has felt too daunting to start. I can finally challenge my thinking to see if I even thought through the project. Then I can evaluate the quality. If it feels unorginal, like ai-slop, or just not good, I can move on and share my learnings.
If I do happen to like what I built, I can keep working on it and maybe, just maybe, actually find something that I love doing and that is mine. That would be true quality.
What’s Coming Next
I’m going to share what I build, and if it’s something that can live on the internet, I’ll just build it right into this blog. I’m going to try and have original thoughts, but still use AI to refine my points, find weaknesses, and make my writing have … more quality.
I might write a post without AI and then have AI be my editor. I could use AI to research a subject and then generate a post. If I do generate anything mainly using AI, even if I’m proud of my prompting, I’ll tag it and share that up front. I am starting to despise getting baited into reading something I think someone put their full heart and mind into, but after a bit it’s pretty clear they either prompted the whole thing or gave up early and let AI do the rest.
I might build a personal finance app with the Plaid personal account connections. I may connect to the Kalshi API and build something in a niche that seems interesting. I’m going to adapt my workflow as I go, share what’s working, what’s not, and what is better talking to Claude rather than reading about it on some low-rent blog.
Stay tuned
If you want to follow along, subscribe to the newsletter, or just check back here every once in a while. Btw, the newsletter isn’t hooked up yet…that will be a future post!