Month: October 2026

AI Setup Evolution

by

I’ve been writing a lot about AI and tech projects lately, which makes sense since that’s the stuff that ends up on this blog. It isn’t all that’s going on in my life, just to be clear. But my AI setup has quietly evolved in August and September in a way that’s letting me undo a bunch of stuff I only built because of the cloud AI’s limitations, so here we go again.

First, the accounts. I’ve been using Claude a lot more than any other AI system lately, but I’m still mixed between Claude and ChatGPT for coding work. Instead of paying for Claude Max or the equivalent top tier ChatGPT plan, which run about five times the price of the regular subscription, I pay for two mid tier plans instead, the Claude Pro and the ChatGPT Plus. Partly that’s so when I run out of tokens on one, I can switch to the other. But that’s a small reason. The bigger ones are that if one gives me a bad answer, I want to try the other, and sometimes I want a second opinion and will ask both the same question. I also don’t think I’d actually use five times the usage, so paying for the bigger plan on either one would just mean I’m not getting my money’s worth. There are times I max out both in the same stretch, so maybe I am doubling up after all. Who knows.

Interesting side note, I’ve been leaning on Codex more for coding lately, with a bit of chat here and there. I like their interactive audio, though I don’t use it as much as I probably hold onto the idea of using it. I’m building sites and things with Codex now, not because I think it’s better, I started because a friend recommended it after I hit a specific wall with Claude. I still use Claude for coding too, but I keep them separate on purpose. Coding work tends to run a project’s token budget down fast, and I don’t want that eating into the day to day chatting I do in Claude. The coding side is pretty interchangeable between the two since everything gets saved locally to wherever I’m working anyway.

Now, the actual problem I’ve been solving. With ChatGPT, and then Claude once I moved to it, the challenge was always context. Take my car tracking prompts as an example. It’s one of many, holiday planning is another, so is tracking the general inventory of stuff I own, but let’s stick with the car since we’re actually replacing it with another used one right now. I’d feed it a lot of detail about the car, our usage, our spending, all of that. Then every new chat, I wanted it to already know the context, how to respond to me for that narrow kind of conversation. So I had some generic prompts, plus a very specific auto inventory prompt, and I’d load all of that into a fresh chat every time.

Then there’s the data itself. Registration, MOT dates, how much we paid for the car, fuel spend over the last couple of months. All stuff AI is genuinely good at trending and drawing insight from, and useful for research too. But I needed to save it somewhere. My old process was to have the prompt itself describe how to save the data, which in most cases meant getting the AI to structure everything into a JSON file I could download and keep a version of.

The problem is I don’t want to keep an indefinite chat going, especially with Claude, though ChatGPT has some of the same issue. As a chat gets long, the AI starts forgetting the earlier stuff and compacts it, and it even warns you this is happening. I wanted everything solid enough that if I deleted that chat and started fresh, the new one would already have everything the old one had.

So the prompts were only half the system. The other half was the JSON, or a CSV for a pure inventory file, sitting there holding the actual data. I built one of these little systems for the car, one for holiday planning, one for holiday budgeting, a stack of them, each with its own context switch. It worked, but it meant a real proliferation of chats. Start a chat, load the data, double check which version of the file I was working from, and when I was done for the day, have the AI spit out a fresh JSON with a version number in the filename and save it to disk. I ended up with thirty or forty versions of some of these files sitting around. Not done with the topic forever, just done with it for that session, so I’d save and move on, and next time load the latest one and keep going.

That whole dance existed because neither Claude nor ChatGPT could write to a file in its own project folder, only read from one. I could load something into a project, but I couldn’t have it write back out to that same spot. That was the actual limitation driving all of it.

Then, much more recently, within the last month or so, Claude’s Cowork got a lot easier to use and a lot more functional. It’s mid September as I’m writing this, and just yesterday I read that they’d simplified the interactions with it even further, which is great timing for me. With Cowork, I’ve gone back through each of my little systems and rewritten the prompts. Now I can just tell a new chat to look at a directory on my computer, read the markdown file with the instructions, read the JSON, and write straight back to that same JSON. No more versioning gymnastics on my end, because I don’t need to care about it anymore. Time Machine on my Mac is already snapshotting everything hourly and backing it up elsewhere, so the versioning is handled at the file system level, which is where it belonged all along.

I still keep these as separate projects in Claude, because I want specific context tied to specific folders on my computer. My car information lives under an auto folder inside a broader life inventory folder, my computers have their own folder, my domain names have theirs, each with its own markdown for how I want it handled. In the past I’d have to manually load the data file and the instructions file into Claude every single time I started up. Now the project just has a tiny instruction pointing to a markdown router, a file in the root directory that lists out all the different contexts I’ve got and where to find the detailed files for each one. It knows to go look in those folders, and inside something like auto, it’ll find an instructions markdown, the data file, and whatever else belongs there. I can start one omni chat for anything life inventory related, or a specific car chat, and either way it’s not my job to keep the local files in sync anymore, because that’s just handled.

For a while I could already do a version of this on my own computer in a coding session, but not from the cloud, not from my phone on the couch, or my iPad while we’re figuring out where to go for dinner or nailing down holiday plans. Now with Cowork, I can start a session that runs as long as it needs to. I don’t care if it compacts and forgets things partway through, because all the data that matters is already saved to a file, and it’s got a remote session into my actual computer at home.

In another post I mentioned why I might end up getting a Mac Mini instead of relying on my MacBook Air, and this is exactly why. If I take the laptop with me, none of these sessions work, since there’s no computer at home to remote into. I’m fine with a dedicated home machine for this, because lately the only reason I’ve been taking a laptop anywhere has been to do AI stuff with it in the first place. It’s a bit circular. If I can run everything through a remote Cowork session back to a computer at home, I don’t need to bring a computer anywhere at all.

I’ve been going on holiday without a computer for a while now, aside from that one AI use case, to the point where I’ve packed the laptop a couple of times telling myself I might need it, and then never actually taken it out of the bag. My 11 inch iPad Pro has become my go to screen for everything, and this new Cowork setup makes that even more true than it already was.

So that’s where things have migrated to for now, and we’ll see how it keeps evolving. Ideally I’d love to get to a point where I don’t need a home computer in the loop at all and can just use remote storage instead. But I don’t use a mainstream service like Dropbox, OneDrive, or Google Drive, which is probably where that kind of direct read and write access would actually get supported first. Last I checked, Google at least would let you read from those places but not write back to them. When that changes, it’ll be worth revisiting, but for now I’m sticking with my own storage.

That’s the state of the AI setup as it stands. Check back in a couple of months to see how much of this I’ve already torn apart and rebuilt again.

The Monitor I Didn’t Buy Yet (and the KVM I Did)

by

I’ve had dual monitors on my desk for as long as I can remember. There was even a stretch when I was single and had more space where I ran three. It’s the same desk I have today, but back then it had a bridge section making the corner, with an L of extra desk where a third monitor lived. It was nice. A computer for one thing, a computer for another. I peripherate on computers. Back then it was the server, the laptop, the work laptop. Now it’s really just personal and work.

The thing is, I’ve almost always run individual setups. One monitor, one machine. Pivot between the two as needed. Lately though I’ve been eyeing a bigger monitor, partly because the ones at work are genuinely nice. Slightly curved, something in the 30-plus range, not as big as I want, but really nice. I also like the idea of a cleaner desk. In the past I used software to move keyboard and mouse across two computers using two monitors and one mouse and keyboard, but my work machine is locked down tight enough, rightfully so, that I can’t install anything like that. So it’s been two keyboards and two mice, physically. Even with an Ergotron monitor arms keeping both screens off the desk, between the monitors, the keyboards, and the speakerphone, it gets cluttered fast.

So I’ve been paused on the bigger monitor for a while. Partly because the one I actually want, the largest decent one that fits my space, costs more than my last computer. I’m hoping the price comes down, or I talk myself into something cheaper, but that’s only part of it. The bigger part is that because it’s so expensive, I don’t want to just pull the trigger and end up unhappy. Unhappy in the sense of: do I actually want single-computer focus, or do I want the ability to pivot between two things running at once? Historically I’ve always liked the pivot. I’ve had KVMs around for probably 25 years, going back to a four-port one on part of my desk at work and a dual one on another when I was building systems. Not something I do now, but clearly that’s foreshadowing where this goes. My kids actually asked me about all this while I was setting it up, which was a fun tangent.

So the thinking became: if I’m not sure the big single monitor is worth it yet, is it worth getting a proper KVM instead and using both monitors I already have, just switching computers on the fly? I’ve tried the manual version of this before, switching monitor inputs by hand between the two computers, and it’s a nuisance. Not fast. Basically a one-time decision each morning (this monitor goes to work, that one stays put) rather than something you casually flip back and forth on, because you’re waiting a minute or two for the input to catch up every time. A KVM is just press a button and it switches. That was the appeal: I don’t need both computers live and visible constantly, but if I need ten seconds on the other one, I can jump over and jump back.

I did the research (with some help from Claude, since I had a pretty specific use case) because both computers are MacBooks with different video requirements: a MacBook Air at home, a MacBook Pro for work. I’ve also got two docks in play, a Dell Thunderbolt Dock WD19TBS for my personal machine, plus a USB-C extender with HDMI I’d been using, and an old Dell D6000 dock from work I could put back into service. I had to give the AI very specific details on exactly what hardware I had, and whether it would actually work together. It came back saying one of my docking stations might be problematic and flagged some KVM models and brands worth looking at. I settled on a TESmart DKS202-MC24, found an open-box unit on eBay about £120 cheaper than new, and also picked up a used Dell WD22TB4 dock, a newer generation than what I had, on the theory it would fix a potential DisplayPort driver issue with my existing setup.

Everything arrived last week and I set it up. The MacBook Air side gave me trouble right away: instead of extending across both monitors, it just mirrored them, which isn’t how it’s supposed to behave. Not entirely sure if that’s on the docking station itself or something about how the KVM sits in between it and the Mac. Either way, the fix was to stop routing that monitor through the dock. That port wasn’t actually spare, I had a mini YubiKey plugged into it, so I moved that over to the dock to free it up, then ran a Thunderbolt to DisplayPort cable I already had lying around straight from the KVM to that monitor instead. Now I’m running two cables: one to the dock, one direct. Not elegant, but it works.

Side tangent I keep circling: I’ve been wondering if I actually want a Mac mini instead of the MacBook Air, even though the Air is fairly new. I’ve been using my iPad more, and I’d rather have a fixed machine at the desk for the remote AI sessions and similar work, which points toward a mini rather than a laptop I’m not really using as a laptop. If something happened to it, we do have an older M1 MacBook Air the family keeps around that my wife barely touches and the kids ignore in favor of their iPads, so there’s a fallback. But that’s getting ahead of myself. For now, the Air setup functionally works. If I went with the Mini I wouldn’t have this dock in the middle of the configuration.

The work side had its own flakiness. Even with the newer WD22TB4, the second monitor doesn’t always get picked up. Same fix: I plugged one monitor directly into the MacBook Pro instead of routing it through the dock. The Pro has more ports to spare, and I wasn’t using that second one anyway, so it’s a reasonable cheat. Both monitors work now. The WD22TB4 kept being just flaky enough, though, that I eventually gave up on it entirely and went back to the D6000 as my daily work dock, with the WD22TB4 sitting unused for now.

Even without any special software, the keyboard plugged straight into the KVM switches between the two computers with a keyboard shortcut, seamlessly. I’m using a Keychron K3 Version 2 wireless keyboard, UK ISO layout, but I’ve got it wired in for this to work, which mildly annoys me since the whole point of that keyboard is Bluetooth. Except this isn’t actually new: even in the old two-computers-two-monitors setup I just left, I had two of these same keyboards wired into each computer anyway, because Bluetooth took too long to wake up whenever I came back to the desk. So wired was always the practical answer, I just needed two cables for it instead of one. Now there’s exactly one keyboard cable on the desk instead of two, which is basically the only real cable left.

Mice are messier. I like Apple’s Magic Mouse, but they pair directly to a computer over Bluetooth, which won’t work with a KVM. I’ve got a Logitech Pebble mouse that does switch between the two machines through the KVM via USB, but I’m not a fan of how the scrolling feels on it. So for now I’m still running two mice on the desk and slowly trying to wean myself onto the Pebble full time.

The end result, though, is pretty good. I’ve been living with the dual-monitor-plus-KVM setup for both work and personal use over the past couple of days. It takes some adjustment, figuring out the habit of what lives on which screen. But so far, so good. I’m hopeful enough about it that I still picture eventually moving to a single unified monitor, which would simplify all of this considerably.

The catch there is that as much as I’d want the monitors closer, they’re honestly already too close because of the metal shelf poles running above my desk. It’s all one unit, so if I pushed the monitors back to give myself more room, the poles would start blocking the view. The monitor I’ve been eyeing, which is by no means the biggest one I actually want, just the biggest that fits my space, would fix some of that and let me adjust things properly. I’d originally wanted something that matched the exact real estate of my two current 27 inch monitors combined, but that simply won’t fit on the desk. And now that I’m actually living with these two side by side, I’m realizing I don’t really use the outer quarter of either screen anyway, since it means pivoting my whole body to see it. So the smaller monitor I’m looking at, and by smaller I mean still around 40 inches, is probably plenty. That’s a topic for another day, if I actually pull the trigger.

For now, so far so good on the dual monitor KVM setup.

And if you read this far the time of 404 was not at all intentional.

Teaching Future Scott to Trust the Money Bot

by

Simplifying my finances is one of those things that’s been on the list forever and just never got looked at. It sat there, neglected, while everything else got attention instead.

Part of the reason is that I spread certain banking functions across different banks. If you follow personal finance blogs, you already know that’s not the recommended move. I try to follow the You Need A Budget methodology, which is the app I use to manage my budget, and the whole philosophy there is keep things as simple as possible. One account, one clear picture.

But my problem is I don’t want all of my money for the month just sitting in a current account. I don’t want that to be where irregular spending, or spending in general, comes out of. Some banks solve this with what people call pots or envelopes, virtual ways to segregate money inside one account. This bill comes from here, that bill comes from there, savings live somewhere else, all under one umbrella. I’m not going to say which bank I use for this, but not many banks in the US or the UK actually offer it, so if you go looking you’ll probably figure it out. The bank I use also has a developer API, which is both potentially dangerous and potentially powerful.

What I wanted was something that could handle the bills coming out of one pot (mortgage, electric, the recurring stuff), set aside money for the credit card bill so it’s always covered when it lands, round up spending a bit each week and stash the extra somewhere, and keep the actual monthly savings separate from all of that. Then whatever’s left sits in the current account for general spending.

The catch is that thing needs constant care and feeding. Bills are fixed, so you pad them a little and move the money over. Paycheck comes in, and you have to decide how much sits where, because I want money sitting somewhere earning interest until I actually need to spend it. It’s a lot of small administrative decisions that need to happen on a schedule, and none of it is hard, it’s just tedious.

So naturally, when you’re a tech person with an API, and a private server sitting at home that you’ve locked down tight, my answer was to build something.

I got access to the developer API and dictated all of it into my notes app first, walking through every use case. Then I fed that into Codex, since that’s what I’m building with these days, and told it what I wanted. It came back and said, yes, absolutely doable, confirming the one thing I already knew I’d need. Everything had to live in one bank, using pots instead of separate current accounts, because the API can only do things within that bank itself, not across open banking connections. That part wasn’t news, it’s why I’d spent the past month or so slowly relocating everything into one place beforehand, betting the API work would do what I thought it could. I was playing the long game on it.

I know at least one or two friends who’ve played with this same API before and had good things to say about it. Someone else at work has built something much bigger with it too, which I’ll get into another time once I’ve actually built my own version of that.

What I ended up with is a website with a UI that tracks the different use cases and, more importantly, the logic rules, because there have to be very specific rules in place so it never moves money it doesn’t have or shouldn’t touch. I built it with a few maturity levels. At the bottom, it’s purely informative, just telling me what’s going on and what it suggests. Above that, semi-manual, where it recommends a move and I go execute the transfer myself. That’s roughly where I am right now, moving from just getting notified to getting a recommendation I still have to act on.

After that, the plan is a warning stage, a day or two heads up before it makes a move on its own, and eventually full automation, where it just tells me after the fact that it moved money, on top of whatever notification I’d get from the bank itself anyway.

The whole point is that if I’m not around to do it, my wife doesn’t have to think about it, and it saves me from manually shuffling money around every week or month. The only thing I’ll still need to do is reconcile it in You Need A Budget, since it’ll pull the transactions in through open banking like anything else. Because the moves are predictable, I’ll know what I’m looking at when they show up.

The logic itself is actually pretty simple. It’s the fact that it touches money that makes me cautious, which is why there are four or five approval levels instead of just flipping it on. The plan is to ratchet it up gradually over a few months, and if it’s consistently accurate after five or six months, I’ll trust it with full automation.

That’s where the AI part gets more interesting, past the point of just building the thing. Once it’s built, I don’t really need AI for it anymore beyond patching bugs or tweaking the UI. The real question becomes whether what I built for manual human intervention is actually the smart way to do it. Is the amount of headroom I gave the bills pot right? Are the intervals right? What actually makes sense here? I’ve asked it to help me look back at a couple months of data eventually and suggest improvements, which feels like the more useful use of AI in this than the building itself.

There’s a part of my brain that’s irrationally nervous about handing this over, even though it can’t make trades and can’t send money anywhere outside my own accounts, and I’ll see everything it does. It’s managed risk, I’d say. But if it works the way I think it will, it saves real time every month, so it’s worth the caution.

Next up, I want to see if there’s a US equivalent I could set up something similar with. My early research says no, but we’ll see.