Dirk Paessler's Personal Blog

Strom ist billiger als Öl – warum merkt man das beim E-Auto so wenig?

Ein Freund fragte mich: Wenn Strom so viel billiger ist als Öl, warum ist das Fahren mit dem E-Auto dann nicht viel billiger? Ich habe nachgerechnet. Die Antwort hat mehr mit Netzentgelten, Ladesäulen-Betreibern und dem Finanzamt zu tun als mit Physik.

Die Frage

Ein Freund hat mir neulich eine interessante Frage gestellt: „Wenn Strom doch so viel billiger sein soll als Öl – warum ist das Fahren mit einem E-Auto dann nicht viel billiger als mit einem Verbrenner?“ Und zwar bewusst nur die Verbrauchskosten, also Strom gegen Benzin. Anschaffung, Wertverlust, Wartung – das ist eine andere Rechnung, die kommt vielleicht in einem zweiten Artikel.

Ich fand die Frage gut, weil sie eine Prämisse enthält, die fast jeder für wahr hält und die trotzdem falsch ist. Also habe ich mich hingesetzt, die Zahlen zusammengesucht und das Ganze in eine Grafik gepackt. Die Kurzfassung vorweg:

Strom ist in Deutschland pro Kilowattstunde nicht billiger als Benzin. Der gesamte Kostenvorteil des E-Autos kommt aus dem Wirkungsgrad – und den fressen Netzentgelte, Abgaben und vor allem die Preise an öffentlichen Ladesäulen teilweise bis vollständig wieder auf.

Terminal Window Wrangling: How I Keep Seven Claude Code Agents Alive on a Mac Mini

One Mac mini, seven projects, one tmux session and about 80 lines of shell script. Survived a reboot, a kill -9 and a dead tmux server. Did not survive my attempt to automate the login.

Two weeks ago, seven Claude Code sessions were running on my Mac mini in seven Terminal tabs. Each one belonged to a project: Captain Drawdown, my Remy skill (my Google Docs skill for Claude), a home infrastructure project, a modelling project for enhanced weathering and some more. I talk to all of them from my phone through Remote Control in the Claude app.

It worked great, until the Mac restarted. Then all seven tabs were gone, and I had to sit down in front of the machine (or connect via screen sharing), open seven tabs, cd into seven folders and type the same command seven times.

I call the fix “Terminal Window Wrangling”: every agent gets a window in tmux, every window runs an endless loop, and macOS itself makes sure the windows exist. No framework, no orchestration layer, no Docker. Shell, tmux and one LaunchAgent.

Remy 0.9: Real Google Docs Suggestions, For Everyone

When I introduced my Remy, the Google Docs skill for Claude, back in August, the article ended with a promise: Update it when Google published the suggestions API officially. Now, here we are!

Untel recently Remy proposed its changes as coloured markup — mint for insertions, pink strikethrough for deletions — because the one thing everybody actually wanted, native Google Docs suggestions with the familiar Accept/Reject buttons, was locked away in Google’s Workspace Developer Preview Program. Preview terms forbid shipping that capability in a public tool. So I wrote: the moment Google makes it generally available, Remy gets it.

That moment came. In October Google promoted the suggested-edits and comments endpoints of the Docs API to general availability — and Remy 0.9.0 was out two days later.

Remy: Working in shared Google Docs with Claude made easy

Almost everything I write these days is written together with other people, in shared Google Docs — reports, papers, blog drafts. And for months there was one collaborator who couldn’t get into the document: Claude.

Not for lack of trying. Claude’s standard Google Drive integration can read a shared document just fine. But it cannot edit one. Ask it to improve your text and it does the only thing it can do: it creates a new file. Ask again, another file. Report-v2, Report-v2-claude, Report-v2-claude-final. Meanwhile your colleagues keep typing away in the original, and you are now the person who merges documents by hand.

For solo work you can live with that. With three people in one document, it’s hopeless.

The job description: invisible sous-chef

So I built Remy — named after the rat in Ratatouille who sits under the chef’s hat and guides his hands, invisible to the guests. That is pretty much the job description.

Geräte-Tauchen im Meer lässt meine LongCOVID Symptome/PEM fast verschwinden. Zum dritten Mal.

Ich habe LongCOVID. Nicht ME/CFS — das muss ich vorweg klarstellen, weil der Unterschied wichtig ist. Mein Fall ist moderat: PEM, Dysautonomie, eingeschränkte Belastbarkeit. Ich bin größtenteils funktional, aber immer mit engem Energiebudget. Menschen mit schwerem ME/CFS leben in einem völlig anderen Energierahmen — ich maße mir nicht an, von meiner Erfahrung auf ihre Situation zu schließen.

Aber was beim Tauchen mit mir passiert, ist bemerkenswert.

The future will be full of software. And full of shitty software. Because…. AI.

After a few weeks of intense work with AI agents, a vision is forming in my head: we’re heading toward a world that is even more saturated with software than today. Especially in niches where nobody would have ever bothered to build code because the effort was too high for too little payoff. Too niche. Not worth it.

That equation is changing fundamentally. The cost of building a piece of software is collapsing toward zero.

I built a searchable directory of 734 CDR companies in one afternoon. Four messages, zero lines of code. This is embedded in an autonomous AI evangelist for carbon dioxide removal – online on four social media platforms with its own website – in a single day. It is not perfect and needs a lot of handholding over time. But way better than… nothing!

What you’re actually building with these AI agents are feasibility studies. They’re not even prototypes (in a traditional software engineering sense). There are no architecture plans, no staging environments, no test systems, no rollout processes – none of the things that make good software good.

Taming this beast feels more like permanent open-heart surgery on a live system.

And yes, you could do all of that properly. But because it’s now so easy to talk a computer into making software, 90% of what gets built will be built by people who have no clue about software engineering, architecture, security, UI design — all the stuff we’ve been learning the hard way for decades.

The result: A lot of shitty software.

I’ve been at this for four weeks now, on the back of 40+ years of software engineering, and it is impressive how far you can get without writing a single line of code.

But not a day goes by where something doesn’t break, or stops working that worked perfectly fine yesterday. It’s constant hand-holding and babysitting. A high-maintenance diva, as I wrote recently.

I’m also absolutely sure that in the next months we’ll hear some crazy stories about people letting their AI agents too far into their lives and their files. Someone’s whole company codebase or work database will get deleted because they gave an agent way too much access.

It will be painful and probably a little bit funny (at least for the onlookers).

Because right now we’re basically handing out very sharp knives. Great tools, but also very easy to hurt yourself with.

So that’s the paradox: AI agents are about to unlock software in a thousand places where it never existed before.

Most of it will be terrible.

Both of these things are true and both of them are exciting.

How My AI Counted Every Carbon Removal Worker on the Planet

What would you do to track companies in a certain industry (here: CDR, carbon Dioxide Removal) and their growth. Part of their process: visiting LinkedIn pages of startups, one by one, and manually counting employees. Copy, paste, next company. Repeat x00 times.

I read that and thought: there has to be a better way. So I forwarded the email to Captain Drawdown — my AI assistant and CDR evangelist — and said something like: “Can you figure out how to get employee data for all CDR companies automatically?”

What happened next was one of those afternoons where you start with a vague idea and end up with something nobody’s ever built before.

Setting Up a Mac Mini with OpenClaw – A Step-by-Step Guide

I wanted a dedicated, always-on machine in my data rack running OpenClaw — three independent AI agent instances, each with its own memory, handling different parts of my work and life. Here is exactly how I did it using Claude Code on a blank new Mac Mini.

Preview: This is how I talk to 5 of my agents through Telegram:

My Zoom / Video-Call Setup: Advanced Tech – Video switcher, Stream Deck, Mountings

Article 4/4

Let’s start with honesty: You do not need a live production console to run a good video call. But if your work depends on video calls and once you have it… you will not want to go back.

The central device in my setup is a “video switcher”, or better, a small video production studio on steroids, the RØDECaster Video, €850.

What changes with a video switcher

The big shift is that it’s no longer “camera → computer → software → meeting”.

My Zoom / Video-Call Setup: Great Video – Three Cameras, One Teleprompter, and Lighting That Actually Helps

Article 3/4

We do video conferences because we want to see each other. That’s the whole point. And yet, in many calls I still see people like:

a laptop camera from below, looking into the nose
a ceiling light that blasts into the camera and makes the person look like a ghost
a super bright window or wall behind a person killing the lighting on the face

As a photographer, that hurts. But even if you’re not: it’s simply unnecessary. You can look significantly better with a few deliberate choices.