Archive: June, 2026

I was reflective about times in my life where it felt beyond great to be in the moment, and how important it is to be present. I still believe that, nothing has changed, but I feel borderline panicked about not having any big "things" on the calendar. No trips, special days, shows or anything else that I really enjoy. That's not a good feeling. (I do have some interviews that are being scheduled, which is good, but not the same thing.)

A large portion of this feeling is related to not working. I became very used to not having to prioritize fun things, which has been great for the purpose of trying new things, hobbies and such. It's unsurprising that my mind isn't exactly one stimulated by "playing in dirt," as they say. Another thing is the deeply ingrained feeling of responsibility I have to being a provider for my little family. I understand why I'm this way (because lots of therapy), and it's hard to pause or reduce that feeling. I feel like I'm not really doing that. Worse, I have to reconcile that with a growing feeling of following my bliss, for me, for whatever that means. That's really hard to act on when I can't even define it.

The usual line of questioning from my therapist starts with, "If you could be doing anything, right now, what would it be?" My brain immediately goes into thought spirals and I can't answer. I mean, the answer is probably, "Run a light show and make cocktails for all of my favorite people at a fundraiser for the arts and GKTW that's happening on a cruise around Norway," but that's not really a thing. (It's hilarious and frightening that my head could generate a sentence like that with little effort.) Ultimately, the negative feelings stem from not seeing a path to some reasonable variation of that.

What's odd about that is that, professionally, that sort of problem solving has been my job for a very long time. Whether writing software myself or leading a team to deliver something, by trade I reduce ambiguity and scope, break down problems into smaller chunks, apply known patterns or new ones, focus the execution and make things happen. I was pretty damn good at that in the last four years in particular. Why is it so hard to do that in my personal life? I guess it's like they say, a therapist can't counsel themselves.

The weeks leading up to that last cruise felt good even when I was idling, which doesn't feel good now because I wasn't really living in the moment. While I was on the ship, I developed the most vivid memories. I'm sure it isn't realistic to apply that expectation to every hour of every day, but it'd be great to get closer to that. To me, that's what living should look like, even when it involves the most simple things.

The Internets are ripe with videos and blog posts telling you that you're doing it all wrong. This isn't really different from anything we've ever seen in technology. People understandably want to sell themselves and appear valuable. But in the last two years or so, I've found that agentic coding involves using a lot of what you might have already been doing.

The overwhelming sentiment is to create more stuff so that Claude gets more right. And then check it when it's done anyway to make sure. For all of the anthropomorphizing that people do with AI, maybe they don't do it enough. I've had pretty good results, and speed, just doing what I already expected to do with humans.

This is the part where I remind people that the longest part of product development is deciding what to do, not how to do it. As engineers will tell you, a lot of our time is spent reducing ambiguity, and getting into fast feedback cycles so we build the right thing. And if you manage engineers, you know that telling them to do something and come back when it's done is disastrous. Yet, this seems to be what people want AI to do. Great, you spun up a dozen agents in parallel, cool story, but was that the goal or requirement? Of course not.

To seed a project, I direct the machine to setup a certain structure, generate some YAML for builds and whatever, and then write how I think the project should be built architecturally in the CLAUDE.md file. I break it up between the natural boundaries of system components. So that means there's usually some kind of API project that's just plumbing to business logic and service classes. I have bits that bridge those to databases, caches, message buses and such. Then I figure out what is the smallest possible thing that I can build, and have it do that, broken up the same way I would for humans, basically creating tasks in each of the above areas.

Feature work goes the same way, splitting it up into the component bits, doing each one, reviewing each batch of changes. For example, direct messaging took about two hours when I added it to TogetherLoop. It's a great example of using the tool to fill in my knowledge gaps. The trick isn't schema or business logic or web sockets, all of which are easy enough to describe and get solid output. But there are a dozen rules around scrolling that I didn't think about, and wouldn't have known how to code without research. It took awhile to get it right, and produce serviceable code, but it was faster than me trying to figure it out. (Full disclosure: I built a similar feature many years ago in POP Forums, manually, and it took a few nights of work.)

What I'm getting at is that this is no different than the way I would treat pairing with others or planning out how to execute something with a team. Yes, Claude does some really stupid things, and is overconfident in its assessments, but you see it, you redirect and you move on. Trying to get it right the first time seems like a colossal waste of time. Fast iteration and doing the next right thing gets you there fast without trying to box it in with pages of text.

No, this is not a reaction to non-employment. It's not that I need the money, it's that I'm not so sure that I need the stuff. I'm kind of foreshadowing some future downsizing, sort of. See footnote.

I've acquired a lot of Lego sets, and realistically, there are a several that I don't see myself building again. Some are more interesting than others. I have a handheld PC for gaming that I thought I would use all of the time, but I just assume use my desktop or Xbox. That can probably be sold. I could probably unload some of my video gear, too, though that would be associated with all sorts of negative feelings because I didn't complete the thing that I bought it for. The DVD collection, which I already reduced by half at the last move, could mostly go. There are boxes of media in the garage that I'll never look at again, or in some cases can't (no telling what's on all of that 1/4" audio tape), but a lot of that just becomes garbage.

I'm not sure what it is, but I feel like I want to be "lighter" and less encumbered. Can't even explain why, since I'm not going anywhere, as far as I know. I feel like I'm channeling "Ryan" in Up In The Air, with his backpack metaphor.

Footnote: Regarding downsizing, there's a part of me that wonders what that would actually achieve, and it raises the issue about the affordability of housing. When I've modeled a move that allowed us to use the equity in our house to buy something outright, it's just not that simple. Property tax and insurance still happen, and even here in our current McMansion, they account for almost half of our mortgage payment. Add the HOA dues and less than half of what we pay actually go toward owning the house. So when I create a budget in today's dollars for what it might cost during "offboardment," there's still a lot of housing expense even if we own the place.

As I sit here listening to "Control Freak" by Armin van Buuren (if you know, you know), I think about how positive I am about so many things. I feel like the world at large is headed toward a turning point. I see positive things happening among friends. My long-term financial prognosis is improving. My health is apparently solid (forthcoming cardiac CT not withstanding).

And yet, there's this thing hanging over my head. The thing is obviously finding another job. One that is amazing and exciting and shows potential the way my job at Angi did. Ugh, it still bums me out. How often do you get to work with the same people for four years-ish that you adore? To be fair, the first month post un-jobbed, I was content to do nothing but do stuff that fed the soul and just mess around. This was followed by a month of concern around Diana's appendectomy and the bizarre complications that came after. But by early March, I was focused on landing a new thing.

I've had four serious loops in that time, and they all ended in defeat for various reasons that either don't sit well or are a mystery. (There's a larger debrief for this to come later.) I'm in two loops now, but I can't easily assume the best, just because of the previous things. It's just so different from 2022, where I was fighting off parasitic recruiters and had multiple options and offers, because I'm experienced. I'm coming off of my most successful job in my entire career. I have numbers that show it. It shouldn't be so hard.

Meanwhile, I built a full-on social network that is fantastic, with all of the features you'd expect. It doesn't invent anything new, but it's ad and algorithm-free, and I love it. I'm not really the marketing type to figure out how to sell it, but it's solid. I look over at the tablet playing music (now it's Sofi Tukker's "Purple Hat"), and love the improvements I've made this year. Heck, I've made some solid improvements on various backend functions of CoasterBuzz, which I haven't touched in years. Agentic AI coding is fantastic. I'm not sure that I've ever been this excited about tech stuff.

But I need another job. One that lasts two or three years would get me to a solid spot that I could in fact "offboard" or whatever. It can be longer, for sure. If the people are awesome and I'm enjoying it, I wouldn't move on. It's not that I don't want to work, it's that I want to do stuff that is awesome. Angi as a company was "meh" in terms of its intent, but I worked with some of the best people I've ever worked with. I miss that.

Trying to disassociate identity with work is harder than I thought.

If you (or your employer) can afford one of the more expensive Apple silicon computers, then you know that the machines can run LLM's well enough. You just need a lot of that unified RAM. More and more people are experimenting with this, and having various degrees of success. This is the foreshadowing that I've been talking about when it comes to an AI bubble. The music analogy is that you no longer need a recording studio if you have a laptop. The AI data centers are the recording studio.

Now Microsoft announced the Surface Laptop Ultra, and the desktop Dev Box. These use Nvidia RTX Spark silicon, an approximate analog of Apple's M-series. This means that the massive power found in the Macs of the last few years will compare to something similar in Windows. The ubiquity of local LLM running ability is coming.

The availability of this hardware, along with increasing end user costs for AI agents, will converge in a way that I think will legitimately harm the big AI companies. I don't know how it will shake out, but the only way it doesn't happen is if open source models can't compete with the "big AI" models. They're already "good enough," if you have the hardware to run them on. That hardware will get cheaper over time.

Agentic coding is certainly just one use of AI, but apparently it's the segment that actually makes money (if not profit) right now. Search and advertising also benefits from this, but Google and Meta own their own infrastructure. Support bots and the like often run on the cloud providers, not AI firms' hardware. While I admire the advancements of Anthropic, OpenAI and such, it's not clear what their long-term play is. Developing great models that eat insane amounts of compute isn't sustainable. And that's not even getting into the pushback from everyone about building data centers.

Don't get me wrong, I think being able to run a local model is a future that we as software people can get into. I've messed with it, and it kind of works with less robust models that will fit in my rig. I need a computer anyway, so if it can do this, why would I pay someone else? Exciting stuff. I don't think it'll be so great for my retirement accounts in the near-term.

Last weekend's cruise was a nice, if entirely too brief, escape from the usual things. The room upgrade was fantastic. When I booked it back in December, I figured that we had not done a proper "us" celebration in awhile, which is how I justified a concierge stay. The upgrade made it feel quite a bit more "luxury," as the suite had a dining table and the primary bathroom was enormous. It had a beautiful mosaic on the bathroom wall above the tub.

Concierge is like having your own little world, with a dedicated lounge, and a sun deck that is wholly underutilized. The Disney ships do a good job at distributing people in various ways, so it never quite seems crowded, but this gives you a level of exclusivity that's pretty extraordinary. The first night we sat in a hot tub by ourselves, and another day we hung out there with just a few other people. They have a bar in the lounge that's open from 5 to 10 everyday, so while we didn't drink a ton (too much food for me!), we didn't pay extra for very much either. Free popcorn, too, which is Simon's "big" expense.

Getting back to the celebration, May 31, 2007, was the day I met Diana, and 19 years later, it still seems like a big day for us. Our wedding anniversary is nice, but the day we met is a day that fundamentally changed our trajectory. It just seems unlikely that we would have met, especially in our 30's, dating online.

We talked for several hours that night, which was not a frequent occurrence in my dating experience, maybe because connection just didn't come easy to me. We talked about theater stuff, our career paths and such. By the end of the year, we moved in together, and married less than 22 months after we met.

I like to think that your outcomes are deliberate, but sometimes you just get lucky. I landed with someone that I'm never angry with, look forward to seeing everyday and I know she supports me in every way. As best I can tell, that's uncommon. I love you, dearest!