Intermediate tag | eYssen AI

93 Articles

Intermediate ×

Vector Databases Without the Jargon

Krisztian Eyssen, Krisztian Eyssen

Vector Databases Without the Jargon

A widespread myth says the vector index eats a lot of memory. According to the vendor's own capacity-planning formula, **the graph is 5% of total memory** — 0.29 GB of index alongside 5.72 GB of vectors. It is the vectors that eat memory. And there is an even more important number: **ten thousand vectors are 75 megabytes.** That fits on a phone. So the question is not whether you need a separate vector database, but **when** — and the answer is usually "later than you think".

Intermediate Developer Explainer Data, RAG & Self-Hosted AI

Sep 13, 2026

Teaching AI Your Own Documents: RAG Explained

Krisztian Eyssen, Krisztian Eyssen

Teaching AI Your Own Documents: RAG Explained

Start with a 910-question benchmark: the same model scored **48.1%** out of the box, **50.4%** after fine-tuning, and **87.5%** with RAG. On another model fine-tuning did not help but **hurt** — from 35.3% down to 21.9%. So RAG is not one option among several: for new knowledge it is an order of magnitude better. It just happens **not to be teaching** — and most of the disappointment comes from believing that it is.

Intermediate Business owner Explainer Data, RAG & Self-Hosted AI

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

Understanding a Legacy Codebase with AI

Krisztian Eyssen, Krisztian Eyssen

Understanding a Legacy Codebase with AI

Model performance **falls off sharply above 32,000 tokens** — while the context window they advertise runs from 128,000 to a million. And there is a measured bias: ask how the repo is put together, and the model would rather **rewrite** it than understand it. This post is about how to ask so that does not happen.

Intermediate Developer Recipe Coding & Development

Sep 13, 2026

Documentation You Will Actually Maintain

Krisztian Eyssen, Krisztian Eyssen

Documentation You Will Actually Maintain

Two independent measurements say the same thing, and both contradict received wisdom: **bad documentation is measurably worse than none**, and the machine-generated "repo tour" **lowered the success rate while making runs 20–23% more expensive**. This post is about what survives all that — not much, but it works.

Intermediate Developer Recipe Coding & Development

Sep 13, 2026

Debugging with AI: A Reproducible Method

Krisztian Eyssen, Krisztian Eyssen

Debugging with AI: A Reproducible Method

On a synthetic, self-contained bug, models get the location right 38–53% of the time. In a real repository, **from the code alone, 1–5%.** The text of the bug report on its own is worth six to thirteen points, and the **order** of the input as much as thirty-seven. This post is about how you hand the bug over.

Intermediate Developer Troubleshooting Coding & Development

Sep 13, 2026

From Prototype to Production: The 70% Wall

Krisztian Eyssen, Krisztian Eyssen

From Prototype to Production: The 70% Wall

There is **no measurement** behind the famous "70%" — the author himself writes that he took it from a tweet. What has been measured: **37%** of companies can show any bottom-line effect at all from AI, and that share has **not moved** in a year — while 80% feel personally more productive. That is the wall.

Intermediate Business owner Explainer Coding & Development

Sep 13, 2026

Buy or Build with AI? The New Calculation

Krisztian Eyssen, Krisztian Eyssen

Buy or Build with AI? The New Calculation

In a survey of 1,719 respondents, **32%** of companies decided **not to buy** at least one piece of software because they built it in-house with AI tools. In the same survey, though, the bottom-line impact attributed to AI **sits at 37% — exactly where it was a year ago.** Building got cheaper. The return did not get better.

Intermediate Business owner Comparison Coding & Development

Sep 13, 2026

Choosing an AI Coding Setup: IDE, Terminal or Cloud

Krisztian Eyssen, Krisztian Eyssen

Choosing an AI Coding Setup: IDE, Terminal or Cloud

In the summer of 2026 one popular AI editor vanished as a product name, and another changed owners. Their pricing stayed; their names did not. Which is why you are not choosing a product but an **architecture** — and there are four questions to settle up front: where the code runs, when you look at it, how much it asks, and who trains on it.

Intermediate Developer Comparison Coding & Development

Sep 13, 2026

Self-Hosted Personal Agents and Their Risks

Krisztian Eyssen, Krisztian Eyssen

Self-Hosted Personal Agents and Their Risks

The security policy of the most widely used open personal agent lists what does **not** count as a vulnerability. This is on that list: **"prompt injection, if it does not bypass policy, authentication, approval, the sandbox or a tool boundary."** And this: **"anyone who can operate an agent can make it do anything that agent is able to do."** This is not a flaw in the system — this is the system. This article is about what you need to know about that before you start it up.

Intermediate Everyone Explainer Agents & Automation

Sep 13, 2026

Browser and Computer-Use Agents: Real Uses

Krisztian Eyssen, Krisztian Eyssen

Browser and Computer-Use Agents: Real Uses

In April 2024 the best model solved **12.24%** of computer-use tasks; a human solved **72.36%**. In August 2026 the best number is **85.96%**. So the capability is there — the question is the cost. And it does not grow linearly, it grows **with the square of the step count**: 6.7 times more steps means a **34 times bigger bill**. The biggest turnaround, though, is somewhere else entirely: the agent that **writes code instead of clicking** is cheaper and more accurate at the same time.

Intermediate Business owner Tool review Agents & Automation

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