Weeknotes

It’s all rainbows and unicorns, and new kitties in this house. And the kids are going zany with joy! Though night time is needing a bit of adjusting. The nightly “hunt” for toes is new to the kiddo’s, so the latest craze everyone-cram-in-bed-with-Mom-and-Dad, now with Cats, let’s just say, it’s the most fun for Mom and Dad.

But for the most part, it is nice having the new little guy around. I seem to have become alpha dad to it. And there’s even more laughter and giggles in and around the house.

Speaking of new things…

I thought it was time to swap out Gemini for Claude for a bit. I herd it was “better”. And it “feels” better so far and warmer to use. The descriptions are very easy to read, plus the little tongue and check infinite thesaurus it uses instead of “working…” is fun. If I had to give a bit of feedb… [You’ve hit your limit]

Are we making a generation of micro-managers?

With my little pet project I’ve been using a developer Agent pretty consistently over the past month, and what I’m finding is as I use it, my language is getting a bit more micro manager-like.

The Pro’s

While I say “micro” manager-y, that’s comparative for me. I’ve always had a more informal, collaborative, less commanding nature to my style. I’ve always been a soft hand.

Maybe this could be making me better at delegation and command like management. 🤔

• Refining my ability to clearly and precisely articulate my request.
• Taking a stronger hand on the reigns to watch and say… whoa whoa whoa there – you’re completely off track.
• Strengthening my ability to look for and argue to look at a problem from a different perspective after it’s got a solution stuck in it’s head and swears it’s right, only to keep failing simple unit tests.
• Nurturing my ability to have and give opinions on nuances I never thought I needed to have.

The Con’s

AI Agents are kinda like brilliant babies at this phase. When they are on, they can baffle the mind on their speed and ability to work. But when they are off… boy are they hammering their heads against the same thing over and over and over again.

It does actually remind my of my children when they were 1-2 years old. Seeing them try and try again.

But, in this “treating it like savant children” thought.. comes the concern.

• The expectation to have an eagle eye view on thought processes
• The decreased patience, i.e. quick to step in and course correction
• The lack of empathy when informing AI it’s not doing a good job
• The lack of creative autonomy

That last one… in dev speak it’s implementation details; in product speak it’s feature factory mindset. You have a biased towards a specific output. Any variation it met with scrutiny and no trust.

All that sounds very way too micro-managery to me.

The hope

The real hope is that people have the ability to choose and transform their behaviours depending on audience… right… right?

So long 2025. Hello 2026.

It the words of a leadership teacher I had, it’s time to ask the check-in questions.

• What went well
• What didn’t go well
• What can I do differently for 2026

What went well

It was my first full year of doing weeknotes, I started at the tail end of 2024. I wouldn’t say I’m prolific and on time with them, but they shake up the excuse for bigger pieces of perfection and got me hitting publish more often.

I touched on every one of Ongs Psychodynamics of an Oral Culture. My own thoughts on it all – the one characteristic of a literate society vs post literate one, is “words are not signs“. in post literate the word “stop” is no different than the emoji “🛑” Now’s the time to stew, fallow, and see what I can improve on and refine.

What else?

• Got a cool new certificate.
• Helping a friend and doing some fun work launching and growing a little candy shop in Whitehorse.
• Started really digging into AI – with a little “vibe” (🙄) coding on a pet project.
• Finally formally ADHD diagnosed. Start seeing what I can do about that.

What didn’t go well

Let’s skim these to stay light:

• The big elephant 🐘 of didn’t go well: furlough to layoff to WTF.
• The body has been a struggle this year.
• Started ADHD meds (yay) switch from private to public health and lost the ADHD meds (boo). All for OK reasons – caution and due diligence and all. But still… I was seeing benefits, and now I’m back to limbo.

What can I do differently for 2026

Not really what can I do “differently” more like, what am I already trying to do differently that I’ll continue or try more of.

Note: there’s aren’t resolutions, I don’t like resolutions. They are more like – I’m-saying-them-out-loud-in-public-so-maybe-I-might-do-them things.

• keep on with the ADHD meds/exploration train
• keep exploring AI to build more things
• getting out into the world, maybe a meetup or conference
• more physical activity

Given last weeks post… it’s been a struggling week. To top it off…

and through it… I’m tinkering. If I’m going to build something and put something in the world, I’ve looked back and it’s likely in December. I get all pensive around my bday, asking what am I doing with myself? And then I go off and make something.

Minimum Vibeable Product

What have I been making? I’ve been sinking my teeth into a little pet project. It’s my own little ActivityPub corner of the internet. And love it or hate it… I’m vibe coding.

I’m working with Google Gemini through Antigravity. And After a couple weeks. It’s fun to be a micro manager of a developer sometimes and, that’s pretty much what you feel like.

I give it some vague detailed order; it does some translating of that order; makes a plan and a todo.; checks with me if I agree, and I do about 80% of the time; then goes off and does it.

I review the code and for me… it’s good enough. After all I’m not going for any developer accolades with my little project. Right now, I’m just going for an MVP.

---

Note: If you’re a developer and want to watch something funny, as it to unit test everything it builds. Watch it argue with it self, sure it’s built perfect code, and then see every unit test fail. And then it argue with itself.

Note II: I now always ensure everything it builds has a corresponding unit test.

Ummm…. what have you made Nano Banana?

I’ve found once Google’s Nano Banana gets an idea in it’s head… it has some trouble letting go.

Here’s how the prompts went:

1. Make me a picture in the style of Ren & Stimpy an interpretive picture of sleep deprivation caused by back pain, flu and children
2. That’s a little too scary for folks… try again more like Spongebob Squarepants, and you don’t need the text.
3. Hmmm. Can you start again? Make me a picture in the style of Spongebob Squarepants an interpretive picture of sleep deprivation caused by back pain, flu and children. No need to add any text where the person sick is a person

Ya, sure. I think I can say that’s been my week on a bunch of fronts. Ship it.

But hey, on the ADHD front?

You betcha I am. Getting certified all over the place!

“Can you make me an image of someone with thumbs up proud to be adhd certified – please don’t add any text“

“Now can you make me an image of me facepalming because of the image you just made?“

“Can you start again, and make me an image of me writing novella length prompts just to get ai to do what I want”