Ya – I’m a little early…

I guess it’s almost the year of the horse or something… I’ve decided to step out from the shadows a bit and start sharing more.

First is all these Tinker Projects. I’m sharing on – https://worktree.ca/ethernick

( note for geeks: I decided to a bit of elbows up by using worktree.ca instead of github )

⁂ ActivityPub + Statamic Playground

• https://ethernick.com – My test site to follow along @nick
• statamic-activitypub-core – A core add-on to out your Statmic site into the fediverse with notes, actors, activities, inboxes and outboxes, and more.
• statamic-activitypub-questions – 🚧 WIP: an extension that will also allow you to get, answer & create your own questions.
• statamic-activitypub-longform – 🚧 WIP: an extension that will also allow you to share articles and custom collections for books & chapters.

♯♭ Music Playground

Aether – A little fun script to take control of my new releases. Create spotify playlists from listenbrainz data

Audio Ether

Part of that Aether script I’m making, I’m building some interesting playlists on my Spotify profile. So, I’m going to make weekly playlists like this. Which are new releases based on my previous plays … which is vast. So far the playlists are turning out nicely.

Update:
Also a monthly exploration post which pulls in the most popular songs of the month, based on listenbrainz plays. I’m still tweaking this script so it’s gonna get better and better. Here’s the first of many.

My ActivityPub pet project is getting super close to being kinda ready for public consumption.

Honestly, I’m just being picky about one last feature, being able to quote people, that I think would make it a real contender from the get go, AKA table stakes.

Sure I could have gone as is without, but I’m so close! Once done I think I’ve got a pretty decent MVP IMO (in my opinion).

More on AI

A few weeks ago I switched from Gemini to Claude. And while it’s nice, I really find myself watching the clock. I’ve got the usage meters up and running and watching and refreshing like a hawk.

I usually hit my quota’s hard and twiddle my thumbs do something else while waiting for the next window to open.

But their lower paid subscript still makes me feel like a second class citizen, enticing me to hit upgrade from $20 to $100 / month.

Change Models, Opus v Sonnet

One thing I did learn from last time, is to mix up the models I’m using. Seems the default was set to their Opus model instead of their other Sonnet model. Which has significantly decreased my quota usage.

Someone equated using Opus to driving a Ferrari in rush hour. Sure, you could, but why?

So now I make the plan with Opus, ensure it’s documenting every nook and cranny, then switch to Sonnet once I start getting into the nitty gritty.

Which One is Better?

The fact that I kind of micro-manage my developer agent I don’t know if the flavours and nuances really matter that much. Maybe if I was in total “vibe” mode and didn’t care under the hood the havoc and mess that could be made, then maybe Claude would win, because it oddly does “feel” a bit better.

However using a concise GEMINI.md, a detailed PLAN.md and, a concise TODO.md – combined with using agent skills, I question whether I would even notice.

That along with not feeling I needed to watch the clock, and a second tier citizen – I’m currently likely to go back to Gemini once I use up my monthly allowance.

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?