Vue lecture

Climb to the Stars

Making the Bees Walk in Line [en]

Par : Stephanie Booth

11 juillet 2026 à 04:01

[en]

Unverified AI transcript (22.07.2026):

Lausanne, 11th July 2026

It’s too hot. Is this the second or the third heat wave? I’m losing count. I think it’s the third, because we’re already hearing about the fourth, right on the heels of the third. So it’s the third, but it’s also just a blur of trying to function day after day in a building that definitely wasn’t designed for this type of weather. Between seven and eight I can enjoy my balcony with Juju. Before it got too hot, I tidied the kitchen, but by the time I was done, somewhere between 8:30 and 9:00, it was already too hot to move. Check the various temperature sensors, close windows, head downstairs for a more static activity.

In addition to figuring out how to function with less energy — still a problem following my accident — I have to figure out dealing with heatwaves. We’ve had them all these last years of course, but this year is way worse. I am so thankful I don’t have an old, sick cat to care for right now, and that Juju is self-maintaining.

Writing on paper is a more linear experience than writing on-screen. Although I’ve always very much been a “first draft” kind of person (even at school, I never made that many changes in between the first “pencil draft” and the “copied copy” I handed in), when typing I am more concerned about the structure of what I’m writing. Not overly, but more. I generally don’t proofread my blog posts, but I do pause whilst writing to read back up and sometimes make some changes as I go along.

Here, I’m approaching writing much more as a “handwriting exercise” (let’s see what it does to my brain!) and so I don’t start writing with a clear intention. It’s stream-of-consciousness, to a large extent. I sometimes write blog posts like that, but less often. A blog post (nowadays) has a TITLE, it’s supposed to be about SOMETHING. Not this. This is about getting legible words on paper with a pen. So I might as well talk-write about something.

The linear experience of lining up words on a page is funneling my scattered hyperactive mind into one direction. Left to → right (write?), the next word can be written in only one place, and once it is written it cannot be taken back. Lines above this one are dead and gone, set in ink, nothing more can be done about them. The only thing that counts is the next word I will write, following the sentence that is taking shape in my head, with the brakes on, because writing by hand is a slow process. As soon as I try to speed up to catch up with my brain, words become scribbles and hand muscles start to cramp.

So it’s interesting. Slowing down is the point. One can train a lot of things, including things our brain does, and “training”, repeating an exercise again and again, is how you train.

I have a lot of trouble resting, stopping, taking a break — not to mention “doing nothing”. Post-accident, I am trying to learn. Actually, I was already trying before (half-heartedly), but now I HAVE to, or the consequences are severe. Lying down and closing my eyes for just five minutes is often impossible, because it’s just too uncomfortable. Try staying still and “doing nothing” when your head is a beehive of thoughts, ideas, emotions, intentions, and desires. Sadly, I often end up scrolling. It gives the illusion of “stopping”, but it doesn’t help the beehive.

So I have a collection of “rest activities”. Jigsaw puzzles. Listen to a podcast or watch a TV series. Read a book. Listen to a song. Physical activity of course, but that’s off the table, particularly with this heat. I’m going to add writing. Not for the content, but for giving my brain a linear experience without input. Because input feeds the bees.

Bees are good. They produce honey. (Can you see I’m tiring?) But when they’re just buzzing around, agitated or angry, no honey is being made. And that helps no one, especially not me.

I will be the queen bee.

Climb to the Stars

Less Input [en]

Par : Stephanie Booth

8 juillet 2026 à 07:37

[en]

In the spirit of shortening things, I’m taking a few moments during my lunch break to share some thoughts I’ve been having recently. Various things have contributed to these thoughts:

my permanent struggle with “too many ideas” and “too many things I want to do” (which predates my accident, but is now exacerbated given my reduced energy)
pondering on how to manage my energy (already underway since my accident, but now fed by the occupational therapy programme for energy management that I’m in the middle of)
my training at IGB, and the two-day course I just did in Paris (the recurring focus is “how something that works for the person at some point becomes the thing that feeds the problem”)
my exploration of AI and in particular the framework/project/took that was previously called PAI (now LifeOS) (output is cheap now: feed a genAI model a few lines and it can spit out thousands of words for you).

I’m not going to be able to reconstruct how my ideas around this have shifted in a chronological or well-organised way, but here’s more or less where I’m at: I’m somebody who believes that “knowledge is power”, that “more information is better”, that by learning and analysing and understanding, I can find answers.

That works a lot of the time, for me. It has worked very well for me. But I’m starting to see how this is part of what is trapping me, right now.

At some point in my struggles with my AI infrastructure (trying to get the PAI Digital Assistant up and running correctly, fixing bugs, making sure it learns correctly, setting up workflows for the things I want it to do for me) I realised that it had a built-in bias (the model, most probably) towards “producing more is better”. LLMs are verbose, we all know that by now. The more you feed them, the more words they spit out – but not necessarily the more useful information.

I kept giving instructions for concision. I would provide examples of how to write things up. I would set up guardrails, have it self-correct, hunt for fluff and filler content. At some point I realised that “the system” was just growing and growing in terms of content (the number of words and files that contained the instructions), and the output was not improving – more like the contrary. This is nothing new, right. We know that complex systems balloon up and lose efficiency. And I’ve seen more than once in my dealings with AI that I pretty much always end up spending more time “fixing the system” than actually using it. This, actually, is something I’d noticed about myself in general; but it’s easier for me to rein in when I don’t have an LLM at the other end of the keyboard. So here, it became even more visible.

So here it is. The mantra I keep repeating to people in all sorts of context: “less is more”; “better is the enemy of good” (that’s what we say in French). If I feed my AI system less input, I get less bloated output in the system. I read somewhere (can’t remember the source, probably have it stashed away somewhere) that in the age of generative AI, the bottleneck was shifting from content production to content consumption. What we can “ingest” is the limiting factor, now that we have machines that can spew out words and sentences and paragraphs and essays and reports like there’s no tomorrow. But it’s worthless unless we can read it and understand it and do something with it. Just feeding that AI output to another AI is just going to magnify errors and biases and produce more slop, unless there is a humain mind in charge that understands what it’s doing and what it’s asking.

Early on, in 2024, I remember reflecting at some point that the AI I was using seemed “more ADHD than me”. And what my more recent experiences have helped me understand about myself is this:

My problem, my “slop/bloat” is ideas and things I want to do. I am somebody for whom ideas are cheap. I have ideas all the time. I can come up with stuff I’d like to do all day. My problem (bottleneck) lies in selecting what I run with, and that is a difficult exercise – even more difficult since my accident.
The more “input” I get, the more – just like the LLM – I produce ideas and desires. I read an article, there are 5 more I want to read. I have a discussion on a topic, I want to read more stuff or write articles or create a community around it. I learn about something new, oooh it’s nice and shiny and I want to do it.

Having a large capacity for input and lots of ideas, followed by enough energy to take a handful of them and run with them (OK, frustrating to have to leave so many aside, but at least I’m busy doing something useful/interesting with some of them) has, as I said above, served me very well in life. But trees don’t grow to the sky. At some point, what has worked well becomes the source of the problem.

And I’m realising that the way out of this, at least now, is not better prioritising. First of all, it’s reducing input.

Less input, less ideas, less “oh I want to do this thing”, less slop to sort through, less frustration with everything I’m not doing.

Exactly how to achieve that is still a thought in progress. But that’s what I’ve been thinking of this last week or so.