[LLMs] Shall we explore coding and AI?


Never apologise, never explain

Right? But argh, it’s so hard when there are so many articles out there like this one, and so many people I know really HATE AI, and sometimes it feels like I’m joining forces with the devil…

So I’m going to try and keep all the apologising and explaining limited to this one post, which I’ll link back to from everything else, and then I can move on.

I’ve started to explore the use of agentic generative AI* to build software.

I was resistant at first, and I’m still not a cheerleader. But, though I have plenty of reservations, I’m not going to lay all the problems of the world at large and our industry in particular at the feet of AI.

The AI Tennis Match Spectator

It’s felt a bit like being at a tennis match this year, watching from the sidelines as people I know and respect either love or hate or (like me) wonder-what-the-hell-about the use of AI in software development.

But love it or hate it, one thing that’s hard is to avoid it. So I’ve joined forces with the devil started playing with it.

I’m not just playing with it, I’m reading about it, I’m researching how to make best use of it, and I’m putting together some workshops (a 2-day workshop for Trifork in Amsterdam, and a one-day workshop at SAG in Berlin, both in Nov) to help others make sense of it too.

Teaching is the highest level of learning

I find that teaching is the highest level of learning, and some of my best teaching is informed by “I can still remember what it was like to learn this, and what mistakes I made.” And I love to learn, and I get even more excited about learning when I know it’ll lead to teaching.

I’m going to document my journey here on Queen of Questions as much as possible**, and aim to share what I’ve learnt along the way.

There are two aspects of this journey - the philosophical and the practical. I’ve been wondering whether I should focus on one aspect or the other, or both at once, or what. I’ve decided I’ll swing between them from post to post. The practical side will likely get more attention than the philosophical, but who knows. This is where that joint-honours degree in Maths and Philosophy I got all those years ago finally comes in handy (or not: I doubt I’ll be quoting Kant’s Critique of Pure Reason any time soon).

So, watch this space! And treat yourself to two days in Amsterdam or a day in Berlin, by signing yourself up for one of my workshops (more info below). Or register an interest in online or in-person trainings. Or contact me if you’d like me to host some training for you and your colleagues.

Agentic Generative LLM AI Mutterings

* Names are hard. What to call it? Agentic AI? Generative AI? Agentic generative AI? All these things mean slightly different things to different people. Agentic because the tools now behave as agents that can act on our behalf. Generative because the tools generate new stuff for us. AI because it’s artificial and it seems intelligent. I’m particularly wary of “AI” because it’s such a vague all-encompassing term and it’s fundamentally inaccurate - they’re not really independently intelligent. So a lot of the time I’m just going to talk about “LLMs” (Large Language Models) because fundamentally, those are the tools I’ll be working with.

** aka: I’m going to make grand promises to myself to write x posts per month, and then settle into something more realistic.

Come on this journey with me

I plan to keep writing about this. I’ve already got a raft of draft posts in pocket. I love to learn, and I love to teach (and I’m really bloody good at it). I use teaching as a way of deepening my own knowledge and pushing me to learn things more effectively.

If you want to know more, you can do the following:

🔗 Want to share this article or save it for later? Here’s a handy link for you!

Clare Sudbery

Don't miss my next post! Subscribe to my newsletter and learn a host of useful tips about coding with agentic AI, as well as learn a bunch of useful stuff about effective technical leadership.

Read more from Clare Sudbery
Matt Squire on stage at Manchester Tech Festival

Matt Squire on stage at Manchester Tech Festival (This is the second post in a series of three, starting here - part 3 may not be published yet.) I was at the always-informative Manchester Tech Festival the other week, where I saw a great talk by Matt Squire, CTO of Fuzzy Labs, with the title "Are We the Last Programmers? AI and the Future of Code". I’ve started experimenting with using LLMs to help me build software, so I'm particularly interested in this topic. Matt covered several areas in...

Snake toy arranged in a pleasing square shape, on a wooden background

I’ve started experimenting with using LLMs to help me build software. One of my background goals in life is to remove or reduce the labour-intensive tasks that hog my time. One way of doing this is to automate. I already have tons of little scripts that do things for me... but I've always found that I'm sloooow at creating those little tools and automations. By xkcd. Permanent link to this comic: https://xkcd.com/1205/ So, recently I've started getting LLMs to help me build stuff to simplify...

Close-up of Clare in a hat, grinning in front of a piano!

This week I am officially "on retreat". I haven't actually left my house because budget, but what I have done is cancel all meetings, turn off all notifications, and I'm not doing any small admin tasks or replying to messages unless they're urgent. It started because I was getting frustrated about how much time each week was devoted to "business as usual", and how hard it was to find large chunks of focused time for the following activities: Reading in depth articles, watching videos etc...