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.
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.
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.
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.
Last week I presented at IDA Driving AI 2026 in Copenhagen. This is the talk retold while it's still fresh
This is the sixth post in a series on AI delegation, trust, and authority. Read the series introduction here. Earlier posts cover authority, reproducibility, visibility, and decision budgets.
One consequence of AI being trained to be so eager to please — the "helpful assistant" persona baked in via reinforcement learning — is that it will make things up. This is perhaps the first difference we must internalise, and where we should be careful not to anthropomorphise the machine too readily. If a human makes things up, we suspect deceit and ulterior motives. An AI's motives are fashioned by that eager-to-please training: it invents references (hallucinations) because it's trying to please you. This raises real questions about how adversarial we want AI to be — an AI trained for brutal honesty may give us better truth-tracking, but at the cost of the compliance that makes it useful in the first place. For now, we can build trust in AI only if we give it a way out to say "I don't know". Most hallucinations I see these days are the prompt's fault rather than the AI's.
An example of where this goes seriously wrong is when an AI is deployed in a responsible, public-facing position with no refusal path. New York City's MyCity chatbot is the most documented case.
The diagnosis that ties the series together: MyCity didn't lack knowledge. It lacked a refusal path. Every one of those answers should have been "I don't know — consult a lawyer or call 311." Instead, every one was a confident paragraph.
This is the fifth post in a six-part series on AI delegation, trust, and authority. Read the series introduction here.
Several prompt-engineering guides out on the web include phrases such as "…and don't hallucinate!" As you may have suspected, this was never going to work. Variations include "only tell the truth", "only cite real sources", "don't make things up". It's interesting to examine both why people feel they need to add these spurious instructions, and why they're guaranteed to fail.
The most striking recent example: on May 4 2026, Marc Andreessen published his current AI custom prompt to 2.1 million views. It's genuinely sophisticated in several respects — and we'll use it as a running example throughout this post — but it still contains the lines: "Never hallucinate or make anything up" and "If you don't know something, just say so." The most-discussed AI prompt of the month has the same hole as the generic advice.
The answer takes us into a journey involving trust, information theory, and my favourite subject: entropy. Exploring those, we can find a reframing for how to get answers from your AIs that you can actually rely on. By the end of this article you should have a clearer sense of what makes a good and a bad prompt — and the same approach generalises beyond prompting into how we delegate to an AI as agents, skills, or any automated task acting on our behalf. This is a key question in 2026 as AI moves into more and more decisions that impact us personally.