Skip to main content
Skip to footer
Opens in a new tab
References
AI Training
Follow-up Courses
Vibecoding Course
Corporate Training (Subsidised)
AI Automation
Pricing
Blog
Contact
Inquiry
Blog
The model knows that it doesn’t know. It just doesn’t know when to stop.
One of the important skills of a reasoning model is not only finding the right solution, but also recognising whether…
When AI Stands Guard
A while back I wrote about the difference between a script, an AI workflow and a real AI agent. The…
Why a Language Model Forgets
In our Facebook group on artificial intelligence, three questions came up within a single week that, at first glance, have…
Script? Workflow? AI Agent? Decide Before You Start Building
A request I get more and more often: “We’d like an AI agent.” Not “we have a problem with orders,”…
Is It Worth Building Your Own “Personal” Apps?
I recently built a simple app to solve one specific problem of mine, one specific need. Under the post where…
What Claude’s planned watermark really does, and how it threatens the future of working with language models
On August 14, 2026, Anthropic announced that future Claude models will embed a statistical watermark in the text they generate.…
Is Plaud Safe?
The Plaud AI voice recorder, a small plastic rectangle the size of a credit card, is currently being talked about…
An LLM is not a calculator, or why not to use language models for calculations and data processing
One successful attempt is all it takes for someone to believe that a language model can do maths. Then you…
New AI usage research: Juniors first in the firing line
Anthropic has released the sixth edition of its Economic Index under the title Cadences, a study built on anonymized data…
Is GEO just SEO in disguise? What Google claims and where it doesn’t add up
The question of whether Generative Engine Optimization (GEO) is a standalone discipline, or merely a marketing rebrand of classic SEO,…
AI Agents in 2026: The (In)visible Security Risk We Invited In Ourselves
This article is based on a talk titled "AI Agents 2026 — The Invisible Security Risk," which I delivered at…
How We Built a Local AI System That Publishes Daily Articles Across 30 Websites
And why combining cloud and local models makes more sense than a pure SaaS solution When you operate a network…
1
2
3
…
5
→