Fabrizio Ferri-Benedetti

The very definition of frolicking.

Yummi

Closed my Mastodon account for various reasons. I'll focus on this one from now on.

I'm afraid the only way to get them to change their ways is by creating skills that work better than theirs, based on docs principles.

New habits for tech writers in the age of LLMs At the end of The writing was always the cheap part, I alluded to the fact that tech writers need to pick up new habits and skills, but didn’t dig into what that entails. These days, any LLM can put t...

Wrote something based on what I'm currently doing and promoting at work. Strong overlap with @tomjoht.bsky.social and Dachary Carey's recent posts, which I take as a good sign. passo.uno/new-habits-t...

Feeling slightly upset as I see developers coming up with Agentic "helpers" fed by docs whose provenance, quality, and maintenance is unknown, eager to just use context as some sort of agentic boilerplate.

If you waaaant!

Docs cartridge

This is one of the possible futures of technical documentation. In some ways, it's already the present.

The writing was always the cheap part Last December, quite unrealistically, I took a solemn oath: I would not write again about AI for at least another year. I was growing tired with the incessant noise, the lack of stability, and the sel...

Good docs require friction, tension, and truth.

passo.uno/real-cost-of...

The writing was always the cheap part Last December, quite unrealistically, I took a solemn oath: I would not write again about AI for at least another year. I was growing tired with the incessant noise, the lack of stability, and the sel...

Inspired by one of @simonwillison.net 's reflections, I wrote a piece on the real cost of technical writing and documentation.

passo.uno/real-cost-of...

The writing was always the cheap part Last December, quite unrealistically, I took a solemn oath: I would not write again about AI for at least another year. I was growing tired with the incessant noise, the lack of stability, and the sel...

Inspired by one of @simonwillison.net 's reflections, I wrote a piece on the real cost of technical writing and documentation.

passo.uno/real-cost-of...

Citroen CX

Every time I listen to Jean Michel Jarre's Equinoxe, I picture myself driving a Citroen CX over a laser grid with a panther on the backseat. Here, I asked Gemini to take a stab at it.

If you're not following @joanwestenberg.com here and elsewhere, you're missing out big time.

Agentic swarms are an org-chart delusion The "agentic swarm" vision of productivity is comfortingly familiar. Which should be an immediate red flag... You take the existing corporate hierarchy, you replace the bottom layers with a swarm of AI agents, and you keep humans around as supervisors. It's an org chart with robots instead of interns. The

The “swarm of agents” model assumes work naturally splits into roles: marketing, sales, support, development = basically mirroring human job titles.

But those titles and siloes are a byproduct of org scaling, not a universal truth about work.

www.joanwestenberg.com/agentic-swa...

In a good way. Best slides assistant.

The worst thing about online learning is that everything has become a video. Every code tutorial. Every design tutorial. Nobody actually writes out a guide anymore. It's just "hey guys welcome to my tutorial" and watching 10 minutes of content that isn't remotely relevant...

"You're the frameworks-and-mental-models person, not the tutorials person." —Claude, about me.

Why did you think so, BTW? :)

I wish.

It's pretty... addictive.

Agent-Friendly Docs | Dachary Carey In which I ask an agent to view hundreds of docs pages - and feel sad.

Don't miss this one: dacharycarey.com/2026/02/18/a...

Well, it happened. I'm on Claude Max.

Claude in PowerPoint Is pretty brutal.

What's the word for someone who's excited and tired at the same time?

I'm extired.

Still from 2010

"Whether we are based on carbon or on silicon makes no fundamental difference; we should each be treated with appropriate respect." — 2010: The Year We Make Contact

An interesting reading on how AI can slow others down and increase their workload.

I haven't written a doc from scratch in like two months. Or a complete doc. Make it three months. I don't know how to feel about it, but I do know that I'm completing more work than before, with the same level of quality as before.

I'm also realizing that it's hard to know when to stop. When you can do more, there's always that "one more task" you'd do with a prompt. It feels like "one more turn" in Civilization. That worries me more than using AI to draft docs.

I haven't written a doc from scratch in like two months. Or a complete doc. Make it three months. I don't know how to feel about it, but I do know that I'm completing more work than before, with the same level of quality as before.

We're testing a docs MCP server I co-developed at work. Agentic workflows, too. We're at a point where we could easily do multi-repo sweeps just by providing a prompt and access to gh CLI. My works is quite different to one year ago — or even six months ago.

And I quite like it.