David Curlewis

Just a quickie based on a few chats I’ve had recently.

There’s no shortage of prominent people talking about how the shape of software teams is changing.

Like many of you (even the ones who won’t admit it), I have a bad habit of scrolling Instagram for a bit when I wake up.

TL;DR We taught the machine to write by feeding it our writing, and now that it sounds like us, sounding like ourselves gets us flagged as “AI generated”; so we contort our voice to prove we are human, and lose the thing that makes our voices ours.

This weekend the weather was a bit crap, so no golf.

It’s fifteen years ago (bear with me, I’ve been in this industry since the late 90s, most of my good stories start this way), and you’ve got two senior developers at a SaaS company.

I’ve led engineering teams in some form for around 15 years now, and recently found myself not quite agreeing with what seems like a fairly common sentiment: that managing AI agents is in many ways the same as leading a team of people.

AI-assisted engineering is now an expectation.

The story so far I shared my AI context system in February… aaaand, it’s already out of date.

In my last post I talked about Peter Naur’s “Programming as Theory Building ” and how cognitive debt is the new thing we should be worrying about (just in case you needed another one 😅).

I recently saw an ex-colleague’s post on LinkedIn referencing a blog by Margaret-Anne Storey on “cognitive debt” which I enjoyed reading, and which sent me down a bit of a rabbit-hole reading cited or related articles and posts, and thinking for far too l…

Just a quickie from me based on a few chats today at work; people see AI-powered workflows and assume there’s serious technical complexity underneath.

I’ve been writing about my AI “memory system” for a while now.

I’ve never claimed to be a good writer, but I’ve always enjoyed writing, so it actually pissed me off recently when I noticed how my last few blog posts were turning into AI slop.

About 18 months ago I started refining and customising how I worked with AI (Claude in my case), as I’ve written about before.

I’ve written about my AI memory system before, which gives Claude a “deeper” memory across conversations.

The third-party transcription app I was using for my AI memory system got flagged as non-compliant at work.

Right… enough context, let’s cut the shit and get to the good stuff.

Last time I talked about giving your AI assistant an actual memory.

If you’re a developer, you’re drowning in AI productivity content.