Autumn 2026

It’s been a couple of months since I wrote a post here. As usual, I’ve got a bunch of stuff on my mind. Let’s see how much of it makes it out and into this post!

I’m thinking about this weekend as being the start of autumn, though I know that was a couple of weeks ago. It doesn’t entirely feel like fall outside (or inside, since my A/C is currently running, so I can keep it under 80° in here), but it’s getting there. And it’s starting to look like fall, at least. The leaves are changing color and falling from the trees. And the Halloween decorations are showing up around town.

Baseball

The Phillies lost game 3 of their wild card series, so I’m mostly done with baseball for now. But I think I may keep watching the playoffs this year.  I subscribed to Molly Knight’s The Long Game newsletter earlier this year, and I’ve been paying a little more attention to baseball in general this season, so I might as well keep watching. (I kind of like the community around The Long Game; it’s fun.)

I ordered a copy of the Ken Burns Baseball documentary series today on DVD, after hearing an interview with him on the Joy of Baseball podcast recently. (This may be another one of those DVD sets that just sits in a pile and gathers dust. I’m in the mood for it right now, but, by the time it arrives, I’ll probably have moved on to something else. But it was only $20.)

Football

I was pretty optimistic about the NY Giants season, up until Jaxson Dart got knocked out for the season in the second game. I don’t know; I still hold out some hope. As I did last year, I signed up for NFL+ Premium, so I can watch RedZone. If the Giants are terrible again, I will at least have something to keep me busy & entertained on Sunday afternoons.

TV

TV is complicated these days. I’d been thinking about re-subscribing to YouTube TV for the football season. I think that, if the Phillies had gotten past the wild card series, and the Giants hadn’t lost Dart, I would have gone with YouTube TV, no question, to continue following the Phillies and to watch the local NY Giants games. But now I don’t know. I convinced myself to look at YouTube TV again today, and noticed that I could get a $50/month promo rate for the “news + sports” package for five months. So I went with that. That’ll give me local CBS & Fox for the Sunday Giants games, and it’ll give me TBS and Fox/FS1 for the MLB playoffs & World Series.

To offset that, I dropped my Disney+ bundle down from the full Disney/Hulu/ESPN bundle to just Disney/Hulu, since YTTV gets me ESPN. That drops the bundle price from around $48/month to $24/month (total w/tax).

And, let’s see, what else…

  • I dropped Netflix in June, but then resubscribed in August, because I wanted to watch the Phillies in the “Field of Dreams” game. But I resubscribed to the ad-supported plan, so I’m paying $9/month instead of $20/month now. And I don’t think I’ve watched anything on Netflix other than the Field of Dreams game, so I should probably drop that again.
  • I let my Paramount+ yearly subscription expire in August, since it would have renewed at $140/year, which is… a bit much. And the whole David Ellison thing is annoying. I never got around to finishing Star Trek: Strange New Worlds season 3, and I didn’t start watching the Starfleet Academy show at all. So there’s a little bit of Star Trek there that I might want to watch eventually. If there’s a Black Friday deal or something, maybe I’ll sign up for another year then.
  • I still have Peacock, which I renewed for only $40/year recently.
  • And I have Frndly TV, which I got for  $96/year in March, largely so I could watch Svengoolie. I’m not sure that’s worth almost $100/year though. Lately, I’ve been using it mostly to binge old episodes of Diagnosis: Murder.

Work

Work is a challenge lately. Next week is when we officially need to start logging our hours. I blogged about that in May, when it was first announced. I’ve just about finished the Mini ETP notebook I bought back then. I’ve got another one one order, to get me through the rest of the year. And I’ve got a 2027 LOTR Moleskine planner to use for next year.

So at least I’m ahead of the curve, since I’ve been writing down my hours in a notebook for the last few months. Figuring out the somewhat arcane system of buckets we’ll be using to log stuff might be a little annoying. We’ll see how that goes.

I got my mid-year performance review recently, and that was underwhelming. It’s kind of a mini-review, so there’s just one rating, and it was “meets expectations”, but I was told that pretty much everyone got that. My boss listed four bullet points to call out my accomplishments, but only two of the four were actually mine. Apparently, he put that together using AI to pull info from Jira, and it got some stuff scrambled up. It’s a little disheartening to realize that your work isn’t really recognized, and that management is just pulling scrambled info from Jira with AI and then not really reviewing it. But I guess that’s where we are now.

We finished our Dynamics AX CU13 upgrade. And boy, was that… bumpy. I have a lot I could say about that, but I probably shouldn’t. I want to say that I’m glad it’s over, but we’re still seeing some lingering post-upgrade issues. This week’s fun issues were: (1) Somebody accidentally decommissioning a live server that they thought was no longer in use. (2) Discovery of a weird CU13 bug that causes the same SQL to randomly return slightly different results. I think I’ve fixed the code there, by changing the way I’m doing things to route around the bug. Since the behavior is inconsistent, I won’t be really sure I’ve fixed it until it’s in production, but I think I have.

I don’t mean for this to seem too mopey. I’m still in a pretty good situation, work-wise, and I’m still having some fun. I may blog later about more specific stuff at work, in terms of my current use of AI / Copilot, but I’m running out of steam here, so I’ll save that for another time.

 

experimenting with Spec Kit

This post is a a follow up to experimenting with OpenSpec from last week. For today’s experiment, I used GitHub Spec Kit. I did this all on my laptop, under WSL. I repeated my Towers of Hanoi project, which I’ve been using for miscellaneous AI experiments. Once again, I used a “requirements.md” file that describes the program I want to write, the same file as I’ve used for the other Towers of Hanoi projects.

Installing Spec Kit is a little harder than installing OpenSpec. You need to install something called “uv” first. Then, you use that to install Spec Kit. (OpenSpec is just a regular “npm install…” thing.)

To start a new project, you do something like this: “specify init towers-speckit”. (This is from bash, before you’ve launched Claude.) That creates a folder with a bunch of template files in it, basically.

After that, you can go into Claude and run “/speckit-constitution”, which is supposed to create a “constitution” for your project. OpenSpec doesn’t have anything exactly like this. I’m not sure how valuable it is; I think a lot of stuff that goes into the constitution could just as easily be in CLAUDE.md. (I guess I can see some point in keeping them separate.)

I’d be interested to see what Spec Kit does with this command, when run on a brownfield project. On a greenfield project, there’s not much to go on, so you’re going to get a pretty generic document. I guess you could go in and fiddle with it yourself, customizing it with your own preferences.

(One interesting side-note here: at no point in this experiment did I get around to creating a CLAUDE.md, nor did Claude / Spec Kit ever suggest that I do so.)

After that, the process looks similar to OpenSpec. You start with “/speckit-specify” to create a spec, then “/speckit-plan” to create a plan, then “/speckit-tasks” to generate a task list, then “/speckit-implement” to actually write all the code.

I found that this process took longer and (probably) burned more tokens than in my OpenSpec experiment. The repo for the project is here.

I had Claude Cowork run a comparison of the two repos, OpenSpec vs Spec Kit, just in terms of size (number of files, etc). In terms of program source, they’re quite similar. Claude thought that the Spec Kit one had “richer test coverage,” but I don’t think there’s a big difference. It noted that Spec Kit has far more spec content (~83 KB vs ~39 KB) and is is overall ~77% larger by byte count. So yes, the idea that Spec Kit is “heavier” holds up.

One other thing to note is that the Spec Kit implementation had a bug in it. If I had actually reviewed the spec, plan, and task docs, I could probably have tweaked them to avoid the bug, but I didn’t do a thorough review of them before proceeding to implementation. So I think that, if you’re just vibing your way through things, SDD doesn’t help that much. Maybe on larger projects it would. But on smaller projects, I don’t think the spec docs are that useful, unless you’re actually reviewing and correcting them before implementation. (It’s kind of like the spec docs we created in the old days; if nobody’s reading them, and thinking deeply about them, then they’re just extra paperwork.)

I’m still undecided as to whether or not I want to start using one of these tools at work. My current workflow for AI development is working reasonably well. I usually create a “plan” doc myself, sometimes with the help of AI and sometimes from scratch. Then, I point the AI at that doc and tell it to implement the feature or fix and update the doc as it goes. Putting more structure around that might be useful, or might just be extra work/bloat.

experimenting with OpenSpec

I’m doing more and more with AI at work, and I’m continuing to experiment with it at home too. One of the guys at work did a little presentation on OpenSpec a couple of weeks ago. He’s really into the whole spec-driven development thing. I’d heard of it, but had never played around at all. I didn’t want to pull it into any of my code at work just yet, so I used it for a project at home.

I went back to my Towers of Hanoi project that I worked on back in February. I used the same “requirements.md” file that I’d used for those experiments. But this time, I first installed OpenSpec, then went into Claude Code, and did something like this:

/opsx:explore Read @requirements.md and help me create a spec.

That spun for quite a while, and spit out a bunch of markdown files, under openspec/changes/add-towers-of-hanoi/. I then continued using OpenSpec’s commands to write and test the code. It worked out pretty well. I think it took longer and burned more tokens that doing it from just requirements.md, as I’d previously tried, but the end result was better. You can see the repo here.

I may come back to it again, and do more experimenting. I’d like to try to use OpenSpec to migrate it from .NET 8 to .NET 10; that should be trivial, but I’d like to see how it does that. And I might also try using it to make the graphics a bit fancier. And there are a few other enhancements I could make. The idea would be to see how OpenSpec handles incremental changes, and what the repo looks like as it goes.

In addition to OpenSpec, I’ve also looked at GitHub Spec Kit. I initially felt like that might be a better fit for my work, since it’s from GitHub/Microsoft, and I’m using GitHub Copilot at work. And it would probably work fine. But it seems like maybe OpenSpec is better for brownfield dev, while Spec Kit is better for greenfield, and all my stuff is (very) brownfield. It also looks like Spec Kit might be “heavier” than OpenSpec, creating a lot more files and doing more stuff. That might be good, or it might not.

Anyway, that’s what I’ve been playing around with this week, in addition to all of my regular ongoing work.

Ghost in the Shell 2026

Between lingering wildfire smoke and random thunderstorms, today has been a good day to stay inside and watch TV. (I did actually do some responsible stuff this morning, but decided to slack off in the afternoon.) So I decided to watch the new Ghost in the Shell anime series, now airing on Amazon.

I have a long history with GITS; you can see some of it here on this blog, including this 2023 post, and this one from 2021.

Ghost in the Shell: Stand Alone Complex is probably my favorite iteration of GITS. Of course, the original manga is great, as is the first movie. The most recent anime version, SAC_2045, was kind of disappointing.

This new version is pretty good, but I’m not sure I like it as much as the SAC series. Only the first two episodes are out, though, so maybe it’ll grow on me. It’s definitely getting a lot of press. Here are a few article links:

I do appreciate that it has more of a “classic” anime feel to it, rather than the janky computer-generated look of the SAC_2045 series.

unicorn experiments

I recently started reading Co-Intelligence: Living and Working with AI by Ethan Mollick. I’m generally leery of AI books, for a number of reasons, but I picked this one up for my Kindle recently, when it was on sale for $2.

There’s a mention, in the chapter I’m currently reading, to an experiment where somebody asked an AI chatbot to “draw a unicorn in TikZ.” I guess the source is this paper. I decided to experiment with this idea a bit myself. The results are in this GitHub repo.

I didn’t specify TikZ, but I asked a few AI tools to write a program to generate a vector illustration of a unicorn, just to see what I’d get.

I started with Claude Code, run via CLI on my Mac, using the default Sonnet model. I was surprised by one thing there: initially, it created and ran its Python code in an ‘artifact’ rather than on my local machine. I hadn’t seen it do that before, at least when I was running from CLI. So that was interesting. I had to, at one point, explicitly tell it to save the Python script to my local folder. I probably need to learn more about that.

The actual result from Claude Code Sonnet was pretty bad. You can see it here. (This is after I asked it to make some tweaks.) And, weirdly, it took quite a lot of “work” from Claude to get this done.

Next, I asked Copilot to give it a try. This wasn’t GitHub Copilot, this was just the web browser interface at copilot.microsoft.com. That gave me an XML file that I could save as an SVG, but no meaningful program code. That SVG is here. It’s not great. I didn’t push Copilot to make it better or anything; I was just curious.

After that, I gave Kagi Assistant a try. As with Copilot, Kagi Assistant isn’t really a coding tool, so I didn’t expect much. But it spat out a Python script pretty quickly, and the resulting SVG looks pretty good. Honestly, better than the previous tests.  This was with Kagi’s “quick” mode, which I think was using Kimi 2.6. As with Copilot, Kagi didn’t give me a ‘real’ meaningful program to generate the SVG. It just gave me a Python program with the SVG in there as a big old string literal, and a couple of lines to write it out.

Finally, I went back to Claude Code, but switched the model to Fable. Rob Conery wrote a post a few days ago, encouraging folks to play with Fable while it was still available. (He was specifically talking about using it against your Obsidian vault, which I also tried, and might write about later.) Fable did a really nice job of writing a good-looking Python script, which output the best unicorn SVG I got out of any of these experiments.

Does any of this mean anything? Probably not. Who knows which of these AI bots is really doing the work, vs. just regurgitating stuff that’s in its training data and/or out on the web. But I learned a few things, and got a few nice unicorn pictures out of it.

NJ PBS

OK, so I guess I’m writing two blog posts today! This one will be short. I was poking around this afternoon and stumbled across the news that NJ PBS is no longer run by WNET and is now being operated by Montclair State University, effective July 1.

I remember reading a while back that WNET was going to abandon NJ PBS, but at that time, it wasn’t clear what was going to happen to it. I guess it’s good that it has found a new home. Here’s an article from nj.com, and an FAQ from the NJ PBS web site.

Here’s an article about a protest letter regarding the sale, from Brenda Flanagan, a correspondent on NJ Spotlight News who retired recently. Here’s an opinion piece by Charles Stile, expressing similar concerns, with some more historical context about the station. And here’s one more article, expressing some concerns from the NJ Society of Professional Journalists.

I’m not sure how all of this is going to work out. I haven’t been watching NJ Spotlight News every day, like I used to, so I’m not sure if they’ve addressed any of this in the regular newscast. I’ve noticed that their video quality has gotten noticeably bad recently, which is probably because they had to shut down their studio and switch to doing it all from home.

If you look at the links in this post, you’ll see that they’re from a hodgepodge of sites, some reputable and some questionable. It’s getting hard to find a good source for local news, especially here in NJ. I hope NJ PBS lives on, in some meaningful way, and I hope NJ Spotlight News keeps running and providing some quality journalism.

an overdue post

Well, I haven’t posted here since May. I’ve had a bunch of stuff I wanted to post about, but I just haven’t had the time (and/or energy).

Tomorrow is July 4th, and a Saturday, so today is the official day off from work for Independence Day. We’re in a bit of a heatwave right now, so I’m not doing anything much for the long weekend. So I thought I’d spend some time writing a blog post today, and trying to catch up on some stuff I wanted to write about.

WordPress 7.0

Well, I didn’t actually intend to write about WordPress 7.0 today, but when I went into my blog admin page, I saw that it was available. So I’m currently upgrading my test site, and will update my actual blog site later, if all is well with the test site.

It seems like the big feature in WP 7 is AI integration. I guess I shouldn’t be surprised about that. Not too long ago, I probably would have rolled my eyes at the idea of having AI integration in my blog site, but, today, I can think of some semi-valid uses for it. Yes, some people are going to use it to create terrible AI slop, but I’ve got a few ideas about how I could use it in a positive way.

Here are a few links related to it:

I haven’t read any of this stuff too closely yet. I’m not even sure how much of it works with the open source WordPress software, vs. how much of it is specific to WordPress.com. Anyway, I guess that researching this stuff and playing around with it is yet another little project for me.

Robot Assistant Field Guide

I mentioned the Robot Assistant Field Guide a couple of posts back. The main part of that class is all done now, but there’s a series of “Robot Builder’s Club” meetings that’s continuing, and those are fun. I learned a bit from this series, though I’m still not really on board with the full robot lifestyle, I guess you could say. I did about 2 hours of busywork this morning (or “donkey work” as David Sparks would say), and I really haven’t automated any of that. But I have gotten in the habit of keeping Claude open while I’m doing work, and using it for little tasks here and there. Here’s some stuff I did today:

  • I had it read all of the 2026 statements for a bank account I have, and create an Excel file summarizing performance YTD, including charts. It did a pretty good job. I didn’t get any new insights out of it, but it was nice. I then also had it create a CLAUDE.md file in the folder with the statements, so I can repeat the exercise, updating the Excel file regularly.
  • I asked it to read and summarize a mutual fund prospectus that I had just downloaded. It called out one upcoming change that’s kind of important: the fund is converting to an ETF next year. I’d stopped reading prospectuses at all, some years ago, but now I’m trying to get into the habit of downloading them and asking Claude to summarize them for me. There’s often nothing big in them, but sometimes, there’s something important.

Overall, I’ve started using Claude as a way to help me analyze my finances and surface trends and opportunities. It’s working better than I would have expected.

The AI Pro

I’m starting to look at something called The AI Pro, from Rob Conery. I signed up for a free account, and I might talk myself into the $300/year paid membership, though I’m not sure about that. I’ve watched one of the free videos, and it’s pretty good. And the material is definitely aimed at folks like me: senior engineers who are getting curious about getting better at AI-assisted programming.

But he uses a service called Circle to host it, and my company (for some reason) blocks that. So I wouldn’t be able to access any of the content from my work computer. In theory, I could ask work to unblock it, but I’m a little hesitant about requesting an unblock for anything that isn’t strictly work-related. I mean, this is clearly a tool that would help me do my job better, but who knows what the powers-that-be at work would think about me bettering myself on company time. (Yes, I know that sounds cynical, but that’s where we are these days.)

Books

I’m currently reading the first book in the Marlow Murder Club series. I’d previously watched (and enjoyed) the PBS series based on the book. I’m enjoying the book too. And I finished the first book in the Thursday Murder Club series earlier this year. Both of these “murder club” books were (presumably) named in reference to Agatha Christie’s “Tuesday Night Club” from The Thirteen Problems, featuring Miss Marple. So that’s another book I need to read, one of these days.

I went on a Kindle book buying binge during the Prime Day sale a week or two ago. I just counted them up, and it looks like I bought… 15 books. Yikes. They were mostly on sale for $2 or $3, so I didn’t break the bank here. But my “want to read” shelf on Goodreads is now up to 928 books.

I’ve also been wanting to switch more of my book buying over from Amazon Kindle to Kobo, but I haven’t been terribly successful at that. Kobo recently announced integration with StoryGraph. I haven’t set that up, but this could be a nudge in the direction of moving away from Amazon/Goodreads over to something else. So I guess that’s yet another little personal project for a rainy day.

Well, I have more stuff I could write about, but I feel like that’s about it for me today. I’ve spent most of the morning doing busy work, writing this post, and generally not doing the kind of things one should do on a holiday. So I think my next stop is the couch, for a quick afternoon nap.

Robert Silverberg

I found myself thinking about Lord Valentine’s Castle, by Robert Silverberg, earlier this week. I read it a long time ago, when it was first serialized in F&SF. I can see here that that was in 1979/1980, so I would have been twelve years old.

At some point, I bought a used copy of the paperback, intending to reread it. Looking through my email, I see that that was in 2010. I never got around to reading that paperback. I went looking for it a few months ago and couldn’t find it, but I stumbled across it earlier this week. (It was in a pile under a bunch of DVDs.) As with a lot of my old paperbacks, I found that the print was too small for me to read, so I put it in my “donation” pile, which will eventually get dumped into a book donation drop box. And I added the Kindle version to my wishlist, figuring I’d buy that version eventually.

That got me looking through my unread Kindle books, which led to me discovering that I had Nightwings in my Kindle library, which I bought about a year ago, for some reason. So I started reading it this week. So far, I’m enjoying it.

Then, in the course of doing some internet searching for info on Silverberg books, I discovered that there’s a Humble bundle running right now, with a bunch of his books! So I bought that, and now I have digital copies of Lord Valentine’s Castle, and all of the other books in that series, plus a whole bunch of other stuff. So that’s cool.

I definitely have too much to read now, and I should absolutely stop buying new books. But I know I won’t. I’m eyeing up the Mercedes Lackey Humble bundle right now. I probably won’t buy that one. I’ve read a few of her books already, and liked them, but I don’t know if I want to add another 37 to my library.

Time tracking and more random experiments

It’s been a busy couple of weeks for me, since my last post. Lots of stuff going on at work, which I won’t get into, since most of it just stresses me out, and it’s Saturday, and I want to think about fun stuff.

One work-related thing that (on the one hand) is kind of stressful, but (on the other hand) gives me an excuse to mess around with some stuff I like to mess around with: time sheets. Yes, after not having to track my time for more than a decade, it looks like I’m going to have to start filling out a time sheet again. The fun part of time sheets is that it gives me an excuse to play around with Sri’s Downloadable Productivity Tools again. I used their “Emergent Task Timer” at my previous job (2010-2012), which was the last time I had to worry about tracking hours. This week, I tried experimenting with their “Emergent Task Planner” form. I printed one out on Thursday, and tried filling it out over the course of the day.

It worked out OK, but the results are kind of depressing. I started the day listing two major projects I wanted to work on. By the end of the day, I had about 30 minutes on the first, and zero time on the second. Then I had about 90 minutes on various support issues, 3 hours worth of meetings, 90 minutes I called “misc admin,” and (the one fun bit) 90 minutes for the “robot club” meeting for the Robot Assistant Field Guide. Technically, I guess I could have skipped that and done some project work, but it was the end of the day, and I was too tired to try to start on “real” work.

For Friday, I wanted to try it again, but Friday descended into chaos so fast I gave up pretty early. For next week, I bought one of these notebooks and will give it a try. I have no idea if I’ll stick with it, but it’ll be a fun thing to play with.

Tracking my time on paper has some plusses and minuses. Since I’m WFH two days and in the office three days, anything paper-based needs to get carried around. That’s not a problem with a small notebook, though I could see myself forgetting it occasionally. My other problem is that my eyesight is so bad these days that paper can be hard for me to deal with. I think the Mini ETP notebook will be fine, but we’ll see. The other dumb problem is that my desk (in the office) is so small that there’s not much room on it to keep a notebook handy. Again, though, I think I’ll be fine, but we’ll see how it works out.

I’ve also been experimenting with creating something kind of like the ETP form in OneNote, so that I can track my time there. That eliminates the various problems with a paper-based system, but it’s somehow not as fun.

I’ve always created weekly notes in OneNote, and made a bullet list for each day, with all of my meetings and all of the projects I’ve worked on. So switching to a daily note isn’t too big a stretch. But then I need to figure out if I want to keep the weekly notes too, or just have the daily notes. I always put a few lists at the end of my weekly notes, for projects I need to work on in that week, stuff I’m waiting on, stuff for next week, and so on. So if I make the daily note my main thing instead of the weekly note, do I move those lists from day to day? Or keep them on a separate weekly note?

One other option is to use daily notes each day, and then have a separate “sprint” note. Our sprints are two weeks long, so that would give me something like the weekly note, but I wouldn’t need a new one every week, just every two weeks. And it makes sense, since our work is (theoretically) supposed to be happening in sprints. But our sprints start mid-week, on Wednesdays, and I’ve never really been able to switch my brain over to thinking about time that way. To me, the standard Mon-Fri work week is still the way I think about things.

One of my problems with doing all of this in OneNote is that I can’t really automate anything there. The Copilot integration for OneNote keeps telling me that it can edit notes for me, but then it keeps failing to do that.

I’ve asked my boss to see if we can get somebody to OK me to use Work IQ CLI, which I think might allow me to do some cool stuff from the command line, though I’m pretty sure it still won’t allow me to automate much in OneNote. I’m definitely starting to think about switching from OneNote to Markdown files, at least for my daily/weekly time tracking. But of course I can’t use Obsidian at work, so that makes it a little harder to justify a Markdown-based system.

I’m not really sure when they’re going to ask us to start entering our time into a system, so I don’t need to start doing this yet, but I always feel like it’s good to get a jump on things, if I can.

On a different topic, I don’t have much to report on the Claude front. I recently switched from using a third-party Fastmail MCP to using the new official MCP. It works well, though I haven’t had a chance to do much with it yet.

I’ve gotten some good ideas out of the Robot Assistant workshops and “Robot Builder’s Club” meetings, though I haven’t actually done much with any of these big ideas. It’s a process, I guess.

I keep finding little things to do with Claude Cowork. Recently, I created an Obsidian note for the upcoming primary election, and asked Claude to add some information to it, based on what it could find on the internet. That worked OK, but then I got the idea to scan in my ballot, and asked Claude to add more information based on that. And that got me a much more complete note. So that was cool.

Well, this post has gotten a bit scattershot, so maybe I should tie things up. Saturday is about half done, but I’ve got all of my chores done, and I think I can spend the rest of the day goofing off.

Claude and Kobo

It’s a quiet rainy Sunday, and I’m pretty tired, so I thought now would be a good time to write up a little blog post.

The first thing on my mind: more experimenting with Claude Cowork. My most recent mini-project was to see if I could hook Claude up to my email. Claude has a built-in connector for Gmail, but of course that’s not what I use. I use Fastmail. I spent a fair bit of time looking at various MCP options. In in end, I went with this one. There are a few ways to get it working, but I went with the simplest one (I think): adding it into Claude Desktop as a Claude Desktop Extension (DXT). That worked well.

I haven’t really done much with it yet. I have a few ideas though. I keep coming back to the idea of some kind of “daily briefing” out of Claude, combining info from my Obsidian vault (tasks), email (newsletters), and news pulled from the web. But I haven’t really gotten far with that.

I just tried this prompt: “Please look at the Receipts folder in my email and find all emails from Kobo. Then make me a list of all the books I’ve bought from Kobo, including title, author, and purchase date. Also, indicate which ones are audiobooks.”

That took a while, but worked pretty well. If I didn’t already have a list of all those books in Obsidian, I could have dumped it into there. I do note that the search took longer than I think it should have; it may be that the MCP I’m using isn’t terribly efficient? Or Claude isn’t using it efficiently? I don’t know.

One thing I’m noticing in my efforts to find good use cases for Claude Cowork: A lot of the stuff that would qualify as “quick wins” doesn’t really help me, because it’s all about information organization, and I’m already really fussy about that stuff. I started watching a video the other day showing how Claude Cowork could sort out a folder full of random documents. The example input folder was full of files named “document.pdf” and “document (2).pdf” and “attachment (3).pdf”. Useless file names, basically. I wouldn’t be able to sleep at night if I had a folder like that! My bank statements for the last ten years are all stored in folders by year and consistently named like “statement-yyyy-mm-dd.pdf”. Same with credit card statements, phone bills, and so on. So Claude can’t help me there!

Another semi-useful thing  I did recently was to pull the annotations from a a book I just finished on my Kobo and reformat them into a nice Markdown file and save it into Obsidian. I use the annotations plugin for Calibre to pull annotations from Kobo books. For Kobo books purchased from the Kobo store, you can export annotations from your account, but for EPUBs that you load yourself, there’s no supported way to pull them. For those, the annotations plugin works, but it’s far from perfect. The annotations show in the book’s metadata in Calibre. They’re in an HTML format, and they’re shown in semi-random order. So that’s frustrating. Claude managed to convert the HTML into clean Markdown, and sort the annotations back into proper order. So I think I’ll be doing that again.

I’ve thought about turning that into a skill, so I can keep using it and get consistent results, but I asked Claude if I should, and it said not to bother. So we’ll see how it works next time. If I see any inconsistency or I can think of stuff I want to tweak with it, I’ll give the skill thing another thought.

So that’s it for random Claude stuff for today. I had to work late on Friday, then all day Saturday, on a server virtualization project, so I should really just be relaxing today and not thinking about computers.