Archive - Fetch Decode Execute

Context engineering in, prompt engineering out

Just like the regular changing of the guard at Buckingham Palace, the term prompt engineering has been marched back to barracks, and context engineering…

Aug 1 •

July 2025

"Big Computers" will save us all!

I couldn’t resist a quick comment on the UK media’s sudden interest in Big Computers, and my annoyance with the shallowness of reporting in the media…

Jul 18 •

ML Pitfalls #3: Data Contamination in LLMs

In this third post in the ML Pitfalls series, I’m going to talk about what I think is one of the most important emerging risks in contemporary machine…

Jul 4 •

June 2025

ML Pitfalls #2: LLMs can't spot ML pitfalls

This second entry in my new ML Pitfalls series follows on from a short post I wrote last year entitled Can LLMs spot machine learning pitfalls?, which…

Jun 6 •

May 2025

ML Pitfalls #1: Classification metrics

I’ve not talked about machine learning pitfalls for a while.

May 23 •

Plumbing LLMs into the world

Plumbing is not the sexiest of pursuits, but life is pretty hard (and messy) without it.

May 9 •

April 2025

Big tech did not invent modern AI

Or why we still need universities

Apr 25 •

Vibe coding: is this really the future?

About a year ago, I mentioned that people were starting to integrate LLM-generated code within their software projects without looking at the code that…

Apr 11 •

March 2025

Reasoning: a small step for LLMs

And a huge leap for LLM hype

Mar 28 •

Stop using 42 as a random seed

This is my 42nd post on Substack, so an auspicious moment to raise an issue that’s been niggling at the back of my mind — people using the value 42 to…

Mar 14 •

February 2025

Can Python be replaced in machine learning?

Every now and then I like to Google “programming languages for machine learning” and then get annoyed by the posts that list every language in the world…

Feb 28 •

The surprising effectiveness of self-supervised learning

Self-supervised learning, or SSL, used to be a pretty niche technique in machine learning.

Feb 14 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts