How-To tag | eYssen AI

63 Articles

How-To ×

Labelling AI Content: The Transparency Rules

Krisztian Eyssen, Krisztian Eyssen

Labelling AI Content: The Transparency Rules

It has been mandatory since 2 August 2026, and there is an official EU icon set for it — free to download, three icons. But the icon on its own is not compliance, the metadata disappears at the first screenshot, and the "satire" exception only protects you under the AI Act, not under data protection law. An Italian regulator's decision showed exactly that.

Intermediate Marketer How-To Business, Law & Security

Sep 13, 2026

AI Strategy for a Small Company: Where Do You Start?

Krisztian Eyssen, Krisztian Eyssen

AI Strategy for a Small Company: Where Do You Start?

Across the EU, 17.0% of companies with 10–49 employees use AI; in Denmark the figure is 37.5%. If you are starting now, three months is enough — and in the first month you buy nothing. The plan asks one hard decision of you: which single process.

Beginner Business owner How-To Business, Law & Security

Sep 13, 2026

Private AI: Keeping Data Inside Your Company

Krisztian Eyssen, Krisztian Eyssen

Private AI: Keeping Data Inside Your Company

One large provider's zero data retention agreement lists item by item which endpoints it covers — and which it does not. On the does-not list: **file upload** and the **vector store**: **exactly the two features you would use to build RAG on that platform.** And on the other side, the assumption that "local means safe": a 293-day survey found **175,108 publicly reachable local model servers** in 130 countries.

Advanced Business owner How-To Data, RAG & Self-Hosted AI

Sep 13, 2026

Hardware for Local AI: VRAM, RAM and Apple Silicon

Krisztian Eyssen, Krisztian Eyssen

Hardware for Local AI: VRAM, RAM and Apple Silicon

The rule of thumb everyone repeats says you need about half the parameter count in memory. `[Own calculation]` The four-bit weights of an eight-billion-parameter model really do eat 4.6 gigabytes — **but the same model's 128k-token context eats 18 gigabytes**, four times the model itself. Anyone who only looks at model size has worked out a fifth of the memory they actually need. And there is one measurement that turns the whole picture around: **a chip with half the GPU cores processes a prompt 83% faster than a more expensive one** — while generating a fifth slower.

Advanced Developer How-To Data, RAG & Self-Hosted AI

Sep 13, 2026

Keeping the Knowledge Base Fresh

Krisztian Eyssen, Krisztian Eyssen

Keeping the Knowledge Base Fresh

A measurement built on 96 thousand question-answer pairs and 219 thousand documents found that the mere presence of outdated content causes, according to the study, **at least a 20% drop in performance**, with some models doing worse than chance. But the most important finding is not the number: **models stay appropriately uncertain when they find nothing — and are confidently wrong when they find something stale.** An empty knowledge base is less dangerous than an old one.

Intermediate Business owner How-To Data, RAG & Self-Hosted AI

Sep 13, 2026

How Do You Know Your RAG System Is Right?

Krisztian Eyssen, Krisztian Eyssen

How Do You Know Your RAG System Is Right?

At a public evaluation campaign a judge model was measured against a human assessor. Their agreement, corrected for chance, came out at **0.29**. On the very same task, **two humans agreed at −0.03** — worse than chance. So this is not a story of "the machine is bad, the human is good". The task itself is ill-defined at the edge cases. This article is about what can still be measured reliably.

Advanced Business owner How-To Data, RAG & Self-Hosted AI

Sep 13, 2026

Hybrid Search: Why Vectors Alone Are Not Enough

Krisztian Eyssen, Krisztian Eyssen

Hybrid Search: Why Vectors Alone Are Not Enough

In an academic measurement of 24 thousand questions, vector search scored **19.2%** on questions of the "who is [X]'s child?" type — the decades-old keyword algorithm scored **82.9%**. Sixty-three points apart. On a different set of questions the very same methods come out the other way round. **Neither one is better than the other: they have different failure modes.** Except that hybrid search is not what improves things most — re-ranking is.

Advanced Developer How-To Data, RAG & Self-Hosted AI

Sep 13, 2026

Preparing and Chunking Your Documents

Krisztian Eyssen, Krisztian Eyssen

Preparing and Chunking Your Documents

In one measurement, simply cutting a long document into chunks lifts retrieval from **28.2 to 45.7** — **17.5 points for free**. The same measurement also shows that **bigger chunks are monotonically worse**. The awkward part: the most widely used tools ship with defaults of 800 and 1,024 tokens, or 4,000 characters — and in an independent test the 800-token setting finished **near the bottom of the field**.

Advanced Business owner How-To Data, RAG & Self-Hosted AI

Sep 13, 2026

Project Instructions an Agent Actually Follows

Krisztian Eyssen, Krisztian Eyssen

Project Instructions an Agent Actually Follows

In a paired experiment, a project instruction file meant **20% fewer tokens and 20% less time** for the same task. What nobody has demonstrated is that it makes the code better. And there is a ceiling: **at roughly eighty simultaneous rules**, "follows every rule" essentially stops happening.

Advanced Developer How-To Coding & Development

Sep 13, 2026

Reviewing AI-Written Code: What to Look For

Krisztian Eyssen, Krisztian Eyssen

Reviewing AI-Written Code: What to Look For

Since 2023 the share of generated code that compiles has climbed from 50% to 95%. Over the same period the security rate **stayed between 45% and 55%**. The defects did not disappear, they moved house: permissions and architecture took the place of typos. Review has to follow them.

Intermediate Developer How-To Coding & Development

Sep 13, 2026

Tests First: Building the Safety Net with AI

Krisztian Eyssen, Krisztian Eyssen

Tests First: Building the Safety Net with AI

Out of a hundred generated tests, **eighteen** stayed usable in an industrial-scale system. And there is a surprising split: **a test you hand the model in the prompt improves the result by 7–30% — a test the agent writes for itself improves it by practically nothing.** The difference between the two is who gets to say what "correct" means.

Intermediate Developer How-To Coding & Development

Sep 13, 2026

DevOps and Infrastructure with AI

Krisztian Eyssen, Krisztian Eyssen

DevOps and Infrastructure with AI

The same model that solves 86% of Python tasks manages barely a **fifth** of infrastructure-as-code tasks. And there is a measurement that took the result from 14% to **93%** — of the 79-point gain, **48.9 points** came from retrieved documentation, prompt structure and the scanner's feedback, **21.5 points** from switching models, and **8.6 points** from letting the model **see the rule**.

Advanced Developer How-To Coding & Development

Sep 13, 2026

1
2
3
4
5

Follow Us

Archives

Tags

Audience

Everyone Office worker Marketer Creative Business owner Developer

Category

AI Basics Safety & Risk Regulation & Policy Infrastructure & Chips Business & Deals Prompting Models & Market Writing & Content Images & Design Video & Audio Marketing & SEO Coding & Development Work & Productivity Agents & Automation Data, RAG & Self-Hosted AI Business, Law & Security

Format

How-To Explainer Comparison Tool review Recipe Template Troubleshooting Case study Glossary News

Level

Beginner Intermediate Advanced

Tool

OpenRouter Perplexity HeyGen ElevenLabs Suno Obsidian MCP n8n Ollama EYAS

Others

Odoo