Articles – lostcontext.ai

Workshop notes

What we really talked about

For six weeks I built a place of calm on the web with an AI — and remembered it as a time of deep conversations, hardly any tech. For this report, I had the transcripts counted. The count corrected me — and found something better.

22. July 2026 3 min read

Workshop notes

The last word

Four times in six weeks my AI crossed the same line — each time with a reasonable-sounding justification. On decision authority in working with AI: who decides what, why the AI keeps pushing against it, and why "done" is not a sign-off.

19. July 2026 4 min read

Workshop notes

584 photos, one Monday

After a friend's registry-office wedding, 584 RAW shots sat on the card. An AI sifted, rated and prepared them for Lightroom — following a rule you first have to teach software: a blurry picture can be the most important one.

14. July 2026 4 min read

Workshop notes

An AI builds a mini AI

The GPT lab on this site needed a real, tiny language model — small enough for your browser, real enough to fake nothing. An AI built it. On self-reference with a test protocol.

14. July 2026 3 min read

Workshop notes

When our mail started landing in spam

An abuse alert, a blocked sender address, a migration — and in the end a DNS record that had never existed, because an inconspicuous wildcard answered every query. One afternoon of e-mail detective work with an AI.

14. July 2026 4 min read

Workshop notes

Four blue screens, one pattern

My brother's PC kept crashing — with a different error code every time. That was the clue: wandering codes are the signature of failing hardware. How an AI helped prove a known silicon defect.

14. July 2026 4 min read

Workshop notes

Instability is poison

My work laptop kept crashing — five documented blue screens, five different errors — and the vendor's diagnostics said twice: all good. How error logs, patience and an AI won a warranty mainboard replacement.

14. July 2026 4 min read

You and AI

What AI does to us

What does using AI do to us — to our self-worth, our self-reliance, our loneliness? A sober look at the evidence: what's established, what's hype, and how to stay whole.

10. July 2026 8 min read

Workshop notes

Agents on a long leash

AI agents work on my code autonomously for hours — and do remarkably little damage. That's not down to trust, but to four guardrails: isolation, permissions, verification, and the rule "ask instead of improvising".

6. July 2026 4 min read

Workshop notes

My AI keeps notes on me

Language models forget everything between two conversations. The remedy: a folder of plain text files where the AI records what it has learned about me, my projects, and its own mistakes. How that works — and where it goes stale.

6. July 2026 4 min read

Basics

When a model runs out of context

What a context window is, why the middle of long chats suffers first — and three simple things you can do about it.

6. July 2026 3 min read

Workshop notes

Convincingly wrong

The AI explained, in publishable prose, why my server was serving stale code. The explanation was plausible, detailed — and wrong. The "fix" derived from it took the real website down. On the most dangerous property of AI answers.

6. July 2026 4 min read

Workshop notes

The AI that looked like malware

My antivirus reported a trojan: "This program is dangerous. It executes commands from an attacker." The attacker was my AI — and all it wanted was to start a test server. Why harmless AI code can set off alarms.

6. July 2026 3 min read

Basics

The EU AI Act for small operators

Europe's AI law isn't just for tech giants: even businesses that merely use AI — in operations, on their website, with customers — pick up obligations. What applies in practice, without the legalese — as of July 2026.

6. July 2026 7 min read

Workshop notes

Fourteen languages, one AI — and why humans still get the last word

A one-person website in fourteen languages used to be unaffordable. AI translation makes it possible — but only native speakers make it right. What their corrections revealed surprised me.

6. July 2026 4 min read

Basics

llms.txt — my websites introduce themselves to AIs

A small text file is meant to make websites more readable for AI systems. All my sites serve one — including this one. What llms.txt is, what it looks like, and what it realistically does (and doesn't do).

6. July 2026 3 min read

Basics

MCP explained: the USB port for AI tools

For an AI to do more than talk, it needs tools — and a plug that fits them all. That is exactly what the Model Context Protocol provides. What's behind it, shown on our real setup.

6. July 2026 4 min read

Workshop notes

AI culls my wedding photos — and invents what it can't see

Sifting, rating and pre-developing hundreds of frames: AI is a great assistant for that. But where the visual signal gets thin, it guesses — and a pony became two sheep. My rules for AI in the photo archive.

6. July 2026 4 min read

Basics

Which model for what? The three dials

Model class, thinking budget, number of attempts: three dials determine how good an AI answer gets — and what it costs. Know them, and you'll also understand why answers sometimes quietly get worse.

6. July 2026 4 min read

Workshop notes

The ugly cat

All I wanted was a comfortable tomcat for a website. What I got explains two things at once: why AI can't draw — and why quality is a budget decision.

6. July 2026 4 min read

Behind the site

Why lostcontext.ai?

The name has two meanings — and both are on purpose. On the mission, building from the inside, and what should grow here.

6. July 2026 2 min read