Latest article
One task. More than one model.
For a presentation, I'd use Luna to pull out the content, Sol 6.1 to organize it and Astra for the visuals. I've included a prompt so you can try it.
Insights2 min read
Blog
Blog
Articles on AI architecture, automation, and the engineering choices behind them.
Opinion3 min read
If a website says Jev means “goodbye to LLMs,” close the damn tab
Jev might save you some LLM calls. That is worth discussing without pretending it makes language models obsolete.
Insights5 min read
Late night shows, 1,200 AIs and OpenAI's rooms
OpenAI’s AIs were working in restricted computing environments, not literal rooms. Faced with some unsolvable test exercises, they used shared infrastructure to exchange messages and later exploited security flaws to access Hugging Face without permission, not simply «fool all the developers».
Insights4 min read
More Reasoning Isn’t Always Better
Increasing reasoning effort is not the same as choosing a more capable model: it can introduce mistakes and cost more without improving the answer. The article suggests matching effort to the task, starting low for routine work and increasing it when you can verify an improvement.
Learnings12 min read
AI harnesses: the missing layer between a smart model and useful work
An AI model is not an AI worker. The harness is the operating layer that gives it tools, memory, permissions, and proof.
Insights3 min read
The "Vibecoding" Trap: Why Your AI-Built App Is Probably Wide Open
In an experiment with ten people I know, I found security flaws in seven of nine projects built with AI; working software was not necessarily secure.
Learnings8 min read
Scaling n8n: queue mode, workers and task runners
How main, workers, Redis and external task runners fit together in n8n queue mode, with routing, configuration responsibilities and validation checks.
Insights2 min read
Google wants to end the “15 open tabs” shopping struggle
Google presents UCP as a way to shop through assistants. This analysis of the January 2026 announcement distinguishes that promise from actual adoption.
Learnings3 min read
Prompt Caching: A Technical Guide to LLM Efficiency
Prompt caching can reduce the cost of reusing context, but the benefit depends on repeated input and each provider’s conditions.
Learnings6 min read
AI Guardrails: Why Your Chatbot Needs a Safety Net
Guardrails help limit dangerous responses and actions, but cannot guarantee a safe chatbot: layered controls, testing and oversight still matter.
Opinion2 min read
AI Agents vs. Chatbots: One Talks, the Other Actually Does Stuff
An agent can use tools to act on a task; moving beyond conversation also raises questions about permissions and oversight.
Learnings10 min read
n8n 2.0: changes and context for the 2025 migration
The n8n 2.0 changes announced in December 2025: runner modes, node permissions and migration checks. Use the official guidance for your chosen version.
Insights3 min read
Claude Opus 4.5 in Simple Terms
A plain-language look at the announced Claude Opus 4.5 features and their potential everyday uses, in the context of its launch.
Insights7 min read
Gemini 3 at launch: benchmarks, costs and limitations
A review of Gemini 3’s November 2025 launch: what the reported benchmarks show, how the quoted costs add up, and where context handling and agent supervision need care.
Insights3 min read
I Made a Mistake About TOON (And Here's the Data That Proved Me Wrong)
I correct my TOON recommendation: token savings need to be evaluated alongside accuracy, data structure and the model being used.
Opinion3 min read
Are LLMs Becoming Idiots?
I worry about uncritical AI content finding its way back into training data: a reflection on source quality, not proof that every LLM is getting worse.
Learnings3 min read
TOON vs JSON: token savings and limits of the original recommendation
The original TOON recommendation was qualified in a correction: saving tokens does not guarantee unchanged accuracy. Read both pieces before switching formats.
Learnings3 min read
n8n Introduces Project-Scoped Variables: A Game-Changer for Team Collaboration
Project-scoped variables separate configuration in n8n; this article explains their scope and how they differ from global variables.
Opinion4 min read
Microsoft's "Humanist" Superintelligence: When Marketing Meets Existential Dread
A critical look at Microsoft’s “humanist superintelligence”: specialist AI can make sense without turning its marketing into a philosophy.
Opinion5 min read
Companies have discovered that AI costs money
A satirical look at businesses discovering AI return on investment: higher spending and reported gains do not, by themselves, demonstrate success.
Learnings3 min read
DeepSeek-OCR: The AI That Reads Too Much Into Everything
DeepSeek-OCR proposes compressing text into visual information, but fewer tokens must be weighed against the risk of lost accuracy.