Posts

I regularly hear about how AI driven development doesn’t work. That’s BS. No, you aren’t going to build a full enterprise application with a single prompt. But you can absolutely build good working software with AI. I recently created Pagelively to host Single Page HTML, Markdown, static sites, etc. on Cloudflare without having to handle a git repo, deployments, etc. It makes it super easy and can be deployed entirely from the cloud without needing to know a single CLI command. ...

As I’ve become a more AI-Driven developer I’ve started to realize that our software repos need to change. And a big part of that change is around documentation. Repos were have always been designed around two consumers: 1) human developers and 2) build/deploy pipelines. For the humans, we organized our code, add comments to code, and occasionally left a few TODO files lying around. For the pipelines, we made sure everything needed to independently build the solution was in the repo and had relative references. ...

After writing my last piece I got to thinking a bunch about the problem of how to live successfully when you don’t really know what is going to happen. Which, to be clear, is always. It’s clear to me that change is accelerating and thus most of us will be navigating what is a more turbulent world over the coming decades. We aren’t built for that, evolution did not select for brains that handle a rapidly changing society because no such thing ever existed. ...

First principles thinking has been a key part of my approach to life since my early twenties. And when I look back at choices I’ve made and said ‘oops, that wasn’t a good call’ I can almost always point to a choice I made without applying first principles thinking. So I try to use it more often than not for any significant decision, even less consequential ones (like, should I buy the television on Amazon Prime Day!) I didn’t buy it, btw. ...

Nic Disclosure: Claude wrote everything here (other than this disclosure). I only provided the cover image from Pexels and I fixed the phrase ‘Last week’ to ‘This week’ in the first paragraph. I don’t necessarily share all the views expressed here, my Wordpress experience was very positive and I think it’s a great platform - I just wanted to eliminate the hosting bill and some the headaches which weren’t worth it for such a simple site. ...

I wrote a piece back at the start of the year called 10 Choices For a Better Future that was largely focused on behaviorally based choices, I now realize. Just to be clear there is no big plan here I just write this stuff when I’m thinking about it and have time and have some motivation. And in discussing this with someone I occasionally mentor recently (okay a couple months ago) I realized that while that list was good from a choosing how to behave daily standpoint (which is what I writing it for) it didn’t really provide any thinking how to make choices about your life, and that’s a problem because you could apply everything in that piece and still make stupid unguided choices. ...

I’m not 100% certain I love this article. I made myself write it in less than one hour. It’s core point is supposed to be around written language being the dominant skill going forward which replaces today’s primary skill of knowing how to do stuff (visual skill). I will likely revisit this topic in the future as I think about it more. For at least the next 5-10 years, professional work is going to become more language-based, not less. We are entering a period where being able to express yourself clearly in writing will be more critical than ever. ...

I had a little fun a few days ago having AI do some forecasting for this weekend DC winter weather event. Figured now that it’s Thursday night I would give the AI chatbots a chance to create a new forecast as we have more updated models. Below is the prompt and the results. I’ve updated my prompt a bunch. I’m really interested in continuing to refine the prompt and using it more frequently. Ultimately I would love to create a process of having it forecast and then tracking accuracy of the forecasts over time. Project for another day! ...

Will it snow? So this is just a quick post on some fun I had this evening with three of the major AI chatbots: Claude, ChatGPT, and Gemini. I’m in the Northern Virginia area and there is a potential winter storm coming this weekend. It has been getting some wild forecast ranges, from maybe a dusting to the Apple Weather app currently showing ~20 inches. So lets just say no one really knows what is going to happen, which is basically true of every winter storm in the DC area. ...

History creates the illusion of predictability once outcomes are already known. Only after events converge do patterns become obvious, narratives become clean, and parallels feel inevitable. Before that point, history is far less useful than most executives, investors, and commentators would like to believe. In theory, history can help us avoid repeating known failures. But even then, it only works when we extract constrained rules grounded in structural invariants - the underlying forces that actually shape outcomes, like capital availability, incentive alignment, and physical constraints. Everything else is pattern matching dressed up as wisdom. And this is problematic, because we often use that dressed-up wisdom to both constrain our choices (“history says that’s a bad idea”) and to make foolish choices (“when in history has this failed?”). ...