In this blog I share my experience in building a Python REPL augmented with ChatGPT. I explore how the application is built, and speculate on software engineering patterns and paradigms that might emerge in systems built on Large Language Models (LLMs).

Hypothesis: How engineers go about delivering code to production has an outsized impact on development and long term maintainability of the system.

As Software Engineers we often talk about the frames of Building the Right Thing and Building the Thing Right. Both contain a number of practices: …

Adelaide on two rolls of film. I left the digital camera at home and instead took the silver tank, the Olympus OM-1 made in 1973. M and I took The Overland train from Melbourne to Adelaide. My last train trip was a few years ago, travelling between Wellington and Auckland on the Northern Explorer. …

A reference for readers familiar with the DORA metrics. This is a mixture of information from the DORA reports, external authors, and my own experience in applying the DORA metrics across a large technology organisation.

If you’re new to the DORA metrics then first read State of the DORA …

Our efforts, those of the ill-fortuned;
our efforts are the efforts of the Trojans.
We will make a bit of progress; we will start
to pick ourselves up a bit; and we’ll begin
to be intrepid, and to have some hope.

But something always comes up, and stops us cold.
In the trench in front of us …