Macbook Air

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.

The Story of My Mac Mini M1

by

I had been waiting for Apple to come out with a new Mac Mini that I can upgrade to for a long time. I even wrote about it as far back as 2016. By then it had been two years since Apple had released anything new in the Mac Mini models. I had the 2012 model at the time. They had came out with a 2014 model however by 2016 when I wanted a new computer it was not worth spending money on a two year old computer model that is only slightly better than the one I already own. The challenge was what I owned was four years old and really needing a replacement.

It would be another two years before the mini was refreshed in 2018. At that point I was prepared to buy a new one. I may have even had an order ready to go. However on reflection the differences between what I had that was six years old in the 2018 variant wasn’t hugely different and the amount of money was not insignificant. At the time I past on an upgrade and just used a laptop as my desktop. I also purchased A significantly cheaper Intel Nuc with better specifications that I put Linux on.

Even after coming up with an alternative plan I still really wanted a Mac Mini. I just couldn’t justify the price for what it was getting me. Flash forward to fall of 2020 and I was excited to pre-order a M1 Mac Mini. I did in fact have an order placed and it was on backorder for about six weeks. After a little while though I talked myself out of getting it and continue to use my old laptop. It was not until this winter then I finally decide the time was right to make a purchase. For the money the mini was a pretty nice computer with the M one chip in it. I also had a 12 inch iPad Pro that are used around the house and out and about like a laptop. It’s not a laptop replacement however someone said the perfect quote that it’s about 90% of our computer replacement. For when I’m not at my desk having the iPad Pro is perfectly fine. For when I sit at my desk having a desktop computer works better than a laptop docked to a monitor.

After literally over four years of waiting I finally got my new mini. Was it worth the wait, I won’t say that. It is a pretty nice computer though. my 2012 mini stop being functional as my main computer about three or four years ago. I used it for a while with Debian on it. At this point it is a paper weight.

I was so slow to write this post that a funny thing happened after a few months with my Mini. I started missing a personal laptop or the freedom that being undocked from a stationary position. Even if it was rare that i did it, the flexibility was nice. I went out and got the stock 8Gig M1 MacBook Air. I was worried that the base configuration was not going to be powerful enough. I was wrong. It has been perfectly fine. After having the MacBook Air a while i can say that i do not use it away from my desk often. When i do it is worth the flexibility. I do see the iPad Pro 12” getting flexible enough that i may change that decision over time.

As great as the Mini was, after about a year I had sold it on eBay in favour of the MacBook Air. I still miss a desktop now and again but the laptop is way more flexible.

Dragon Dictate 3 Upgrade

by

Since I like writing, but typing at the end of the day after working at a computer all day is not the most fun thing to do I have been using dictation to write. It has been fantastic.

The issue is since I upgraded to mountain lion my dictation software on the Mac has not been working. I’ve actually been using the dictation on my iPhone 4S. I think I’ve written about that before. It’s actually quite good, but nowhere near as good as using the computer. As if to prove a point, the WordPress app on my iPhone 4S just crashed for the second time in a day. I lost about two paragraphs of this post and had to write it over. That sort of thing doesn’t happen on the Mac.

Today, Nuance the makers of Dragon Dictate released an upgrade for Dragon Dictate for the Mac that works with Mountain lion. Because of the limitations of the iPhone dictation I am pleased to be able to upgrade. But I’m not pleased about is the rather expensive price of the $149 to be able to upgrade. I don’t typically buy software is expensive. The only other software that comes anywhere close to this price is Microsoft office. Even that I got a rather steep discount through work the last upgrade. I just hope the price was worth it.

I am downloading it now, and I hope to have it working tonight. I’m wondering if I need to train it again. This software I like the mobile phone versions of the software requires you to train the software by reading. It does not take very long, but it does require some minor concentration to read to a computer. I will give my opinion in a later post.

Desk Reconfiguration

by

At work I have had 5 monitors on my desk.  Let’s not argue the necessity of five monitors. It is a bit excessive. That is why I’ve been thinking about downsizing for a while.  At the time the setup made sense, and I had the equipment on hand so I figured why not.  Recently however my desk is been slightly cramped, and I found myself using my third computer significantly less.  This set up started when I got a new 27 inch display for my laptop.  It was a great needed addition since the extra real-estate is used and I blow text up a lot.  With that addition I had the two 19″ monitors I was using for my Macbook Air free to move to my Mac Mini that I use.  I have that machine mainly to sit on the guest wifi network to do Skype video chats with far flung staff.  I can use Skype on the internal network but it never seems the same.  The 15″ monitors (2 of them) I was using for the Min went towards a Dell desktop I have that I run a specific work app on.  I can run it in a VM but on my older Macbook Air the VM was starved for memory.  Now i may revisit the need for that machine but i like having a dedicated Windows machine around even if I dont use it often.

Since I wasn’t using the windows machine a lot I gave away the 15″ monitors and just have the Dell desktop plugged into one of the Mini’s 19″ monitors.  They take DVI & VGI so I created  poor mans switcher for the monitor.  Longer term i will probably just RDP to that machine.  Surprisingly 3 monitors is not uncommon at work.  Some people even have 4 but i was a bit out there with the 5.

Now I have space on my desk that you can actually see my wedding & engagement photos.  Now isn’t that whats important?

Next Gen MacBook Air

by

After much pondering I broke down and put an order in for a new MacBook air 13 inch. I bought a 2011 model last August and I’ve been very happy with it, except for a few drawbacks. The new model seems to correct all the drawbacks I’ve experienced. The only thing I had to do to get it was spent a lot more money for it. I think it’ll be worth it in the long run. I have been generally upgrading laptops every year so, and in the near future I don’t think that’s going to happen with a baby on the way so I want to get the upgrade out-of-the-way and be happy with additional capacity now.

This new MacBook air is sporting eight gigs of RAM and a 512 gig SSD drive. The old model didn’t have enough memory for what I was using it for, especially running a virtual machine. I also maxed out the 256 gigs on the old one SSD, so going for the 512 gig SSD was a must. But that upgrade broke the bank. I contemplated going for a MacBook Pro 13 inch with the regular hard drive but the cost difference and the performance difference really didn’t make it worthwhile for me. I’ve been spoiled with the SSDs in the Air’s for the past two years so going back to a 5400 RPM hard drive wasn’t really something I wanted to do. Other notable improvements is the USB three, but I really don’t have any use for it at this moment. Also the Core i7 dual core processor is slightly faster than what I’ve been used to all my old air.

It doesn’t come with Mountain Lion, but I get a free upgrade when it comes out in a few weeks.  I will probably buy the upgrade anyway since I have other computers I want to upgrade anyway, and the free upgrade is only for this laptop.

So far I’ve been extremely pleased with the upgrade. Now all I have to do is eBay my old laptop.

The New MacBook Air

by

This week turned out to be a two laptop week.  I was already thinking about selling my existing 2010 Macbook Air and upgrade to the new i5 2011 Air’s that just came out in July  when I convinced M to order a new Macbook Pro but I finally pulled the trigger on the new Air today.

I was waffling for a while since the 2010 model is still perfectly good.  The big drawback for me was the processor wasn’t anywhere near a desktop or even a bigger laptop’s speed.  That changed when the new i5 Air’s came out.  After figuring how much i could sell my old Air for i decided to make the jump and upgrade.

I have bought lots of stuff at the 5th ave Apple store but today was actually the worst experience i have ever had there.  It was super crowded and it took forever to find someone to help me, only to have them tell me oh you need to find a free computer and tell the ipad sitting next to it you need assistance and then you will go into queue to get help.  Problem there is everyone is on these laptops for hours surfing Facebook and two no one tells you that is the process.  I have bought more than one computer from this store and this is the first time i have ever had to do that.

Drama aside i was able to get the model I wanted and headed home.  Well after more minor train drama i was able to get home but that is another story.

I had already taken a backup of my old Air using Carbon Copy Cloner so setting up this computer was as simple as plugging in the backup hard drive and saying yes restore from an external hard drive.  For that function alone i have to love Apple!

 

 

Trying Outlook 2011

by

Busy day at work today. I took a call at 8AM at home and then ran to the office after that. Full day of calls later I am pretty tired.

I did eak out some time to try using Apple Mail with exchange. I couldn’t really do it well before getting migrated to Exchange 2007. Now that I am moved over I gave it a try. i did so also a few weeks ago briefly but played with the settings a bit more today. Short summary for me is i like the ability to see threaded conversations in all folders in one view like in Outlook 2010, but otherwise not very happy. I will continue to use Outlook 2011 when running on my Macbook Air or Outlook 2010 in a VM.