A large part of AI engineering these days is selecting which model is best for which task, a bewildering choice that is getting more complex, not less, over time.
Work has continued over the summer on the AIPLA project which has created several new features and insights that I would like to catch up on in this week’s post.
Lots of people back from summer holidays now so less technical work this week, but that gives me a chance to step back and examine the AI projects I’ve been working on and start to analyse what really gave value.
A couple of weeks ago I wrote about the dark factory loop being used to self-improve AILANG, the programming language designed for AI rather than human programmers.
I know this newsletter can be very in-the-weeds as I explore AI’s frontiers. But this is a very practical post, I hope, as alongside my AI engineering work this summer I had a second job: selling and buying a house for my family.
There is a lot of noise in AI trends which can seem abstract or theoretical to those not following every day, so I’ll try not to add to that but instead show a public example of a living, breathing open source project and how it is using terms like “loop engineering”, “dark factories” and “agent graphs” to get things done today.
I’m currently working on two projects that have both converged to a pattern I think will become a standard in AI-human co-creation.
I’d never been to Croatia before this weeks visit to Opatija for WebSummerCamp ( https://websummercamp.com/2026 ) but I hope to visit again very soon this beautiful seaside luxury resort that feels like an undiscovered secret gem of a place and community rumours of which has not quite yet reached Copenhagen.
As you may have heard, Anthropic was forced by the U.S. administration to revoke access to its latest Fable 5.0 model due to security concerns, and it may only come back as usable by U.S. citizens. This has sparked off various reactions across Europe on AI sovereignty which should be addressed.