Tags: cog

49

sparkline

Wednesday, March 18th, 2026

Working with agents doesn’t feel like flow — Bill de hÓra

Related to Matt’s thoughts:

…working with agents feels much less like classic deep work, and much more like playing a game. Not to say the work is frivolous—it’s just because it feels like I’m in a game loop.

Flow, at least in the usual sense for me, feels smooth and continuous. The work and your attention starts to line up so cleanly that the experience becomes frictionless. You disappear into the work and meld with it. One notable aspect of flow has been I lose track of time. Working with agents on the other hand, is not like that at all. It’s highly engaging, but in a more jagged, reactive way. I’m focused, but not settled. I’m absorbed, but not merged with the task. I’m paying close attention the whole time, but the attention is dynamic and tactical rather than continuous. I don’t lose track of time at all.

Wednesday, March 11th, 2026

I work, I think? - Annotated

This is about something that’s already happening, that doesn’t show up in employment figures: the quiet destruction of the feedback loop that turns inexperienced people into competent ones. The process by which you get something wrong, feel it, understand why, and become slightly less wrong next time. It’s unglamorous and it’s slow and it’s the only way it’s ever worked.

AI short-circuits that learning completely. Not maliciously. Just structurally. When you can generate something that looks right without doing the thinking, you will (most people, most people being me, will, most of the time, under pressure, with a deadline) and the muscle that thinking would have built never develops.

Wednesday, March 4th, 2026

Feedback

If you wanted to make a really crude approximation of project management, you could say there are two main styles: waterfall and agile.

It’s not as simple as that by any means. And the two aren’t really separate things; agile came about as a response to the failures of waterfall. But if we’re going to stick with crude approximations, here we go:

  • In a waterfall process, you define everything up front and then execute.
  • In an agile process, you start executing and then adjust based on what you learn.

So crude! Much approximation!

It only recently struck me that the agile approach is basically a cybernetic system.

Cybernetics is pretty much anything that involves feedback. If it’s got inputs and outputs that are connected in some way, it’s probably cybernetic. Politics. Finance. Your YouTube recommendations. Every video game you’ve ever played. You. Every living thing on the planet. That’s cybernetics.

Fun fact: early on in the history of cybernetics, a bunch of folks wanted to get together at an event to geek about this stuff. But they knew that if they used the word “cybernetics” to describe the event, Norbert Wiener would show up and completely dominate proceedings. So they invented a new alias for the same thing. They coined the term “artificial intelligence”, or AI for short.

Yes, ironically the term “AI” was invented in order to repel a Reply Guy. Now it’s Reply Guy catnip. In today’s AI world, everyone’s a Norbert Wiener.

The thing that has the Wieners really excited right now in the world of programming is the idea of agentic AI. In this set-up, you don’t do any of the actual coding. Instead you specify everything up front and then have a team of artificial agents execute your plan.

That’s right; it’s a return to waterfall. But that’s not as crazy as it sounds. Waterfall was wasteful because execution was expensive and time-consuming. Now that execution is relatively cheap (you pay a bit of money to line the pockets of the worst people in exchange for literal tokens), you can afford to throw some spaghetti at the wall and see if it sticks.

But you lose the learning. The idea of a cybernetic system like, say, agile development, is that you try something, learn from it, and adjust accordingly. You remember what worked. You remember what didn’t. That’s learning.

Outsourcing execution to machines makes a lot of sense.

I’m not so sure it makes sense to outsource learning.

Monday, March 2nd, 2026

The nature of the job

Large language models help you build the thing faster, which is the primary end goal for your company but only sometimes for you. My primary goal might be to build the thing faster, but it also might be to learn something durably, to enjoy the work, to look forward to Monday.

I don’t like the mental fragility of not fully understanding how my own code works, where AI-generated code is “mine” in that it’s attributed to me in the git blame and I’m its maintainer going forward.

Friday, February 20th, 2026

Training your replacement | Go Make Things

I’ve had a lot of people recently tell me AI is “inevitable.” That this is “the future” and “we all better get used to it.”

For the last decade, I’ve had a lot of people tell me the same thing about React.

And over that decade of React being “the future” and “inevitable,” I worked on many, many projects without it. I’ve built a thriving career.

AI feels like that in many ways. It also feels different in that non-technical people also won’t shut the fuck about it.

Wednesday, February 18th, 2026

How Generative and Agentic AI Shift Concern from Technical Debt to Cognitive Debt

I recently wrote:

The issue isn’t with the code itself, but with the understanding of the code.

That’s the difference between technical debt and cognitive debt.

John has written lots more on this.

Sunday, December 7th, 2025

The Jeopardy Phenomenon – Chris Coyier

AI has the Jeopardy Phenomenon too.

If you use it to generate code that is outside your expertise, you are likely to think it’s all well and good, especially if it seems to work at first pop. But if you’re intimately familiar with the technology or the code around the code it’s generating, there is a good chance you’ll be like hey! that’s not quite right!

Not just code. I’m astounded by the cognitive dissonance displayed by people who say “I asked an LLM about {topic I’m familiar with}, and here’s all the things it got wrong” who then proceed to say “It was really useful when I asked an LLM for advice on {topic I’m not familiar with, hence why I’m asking an LLM for advice}.”

Like, if you know that the results are super dodgy for your own area of expertise, why would you think they’d be any better for, I don’t know, restaurant recommendations in a city you’ve never been to?

Wednesday, May 7th, 2025

You Can Be a Great Designer and Be Completely Unknown - Christopher Butler

Great design isn’t defined by who knows your name, but by how well your work serves human needs. It’s measured in the problems solved, the frustrations eased, the moments of delight created, and the dignity preserved through thoughtful solutions. These metrics operate independently of fame or recognition.

Our obsession with visibility also creates a troubling dynamic: design that prioritizes being noticed over being useful. This leads to visual pollution, cognitive overload, and solutions that serve the designer’s portfolio more than the user’s needs.

Wednesday, March 26th, 2025

A fiddle on a round table in front of a woman playing the harp in a pub.

Wednesday session

Wednesday, January 15th, 2025

Prescriptive and Descriptive Information Architectures | Jorge Arango

Interesting—this is exactly the same framing I used to talk about design systems a few years ago.

Sunday, June 16th, 2024

Your brain does not process information and it is not a computer | Aeon Essays

We don’t store words or the rules that tell us how to manipulate them. We don’t create representations of visual stimuli, store them in a short-term memory buffer, and then transfer the representation into a long-term memory device. We don’t retrieve information or images or words from memory registers. Computers do all of these things, but organisms do not.

Wednesday, July 13th, 2022

How normal am I?

A fascinating interactive journey through biometrics using your face.

Wednesday, June 1st, 2022

What the Vai Script Reveals About the Evolution of Writing - SAPIENS

How a writing system went from being a dream (literally) to a reality, codified in unicode.

Sunday, March 7th, 2021

This Word Does Not Exist

This is easily my favourite use of a machine learning algorithm.

Thursday, January 28th, 2021

Historical Dictionary of Science Fiction

A fascinating crowdsourced project. You can read the backstory in this article in Wired magazine.

Saturday, December 26th, 2020

Talking out loud to yourself is a technology for thinking | Psyche Ideas

This explains rubber ducking.

Speaking out loud is not only a medium of communication, but a technology of thinking: it encourages the formation and processing of thoughts.

Friday, August 28th, 2020

Make Me Think | Jim Nielsen’s Weblog

The removal of all friction should’t be a goal. Making things easy and making things hard should be a design tool, employed to aid the end user towards their loftiest goals.

Thursday, January 23rd, 2020

Web standards, dictionaries, and design systems

Years ago, the world of web standards was split. Two groups—the W3C and the WHATWG—were working on the next iteration of HTML. They had different ideas about the nature of standardisation.

Broadly speaking, the W3C followed a specification-first approach. Figure out what should be implemented first and foremost. From this perspective, specs can be seen as blueprints for browsers to work from.

The WHATWG, by contrast, were implementation led. The way they saw it, there was no point specifying something if browsers weren’t going to implement it. Instead, specs are there to document existing behaviour in browsers.

I’m over-generalising somewhat in my descriptions there, but the point is that there was an ideological difference of opinion around what standards bodies should do.

This always reminded me of a similar ideological conflict when it comes to language usage.

Language prescriptivists attempt to define rules about what’s right or right or wrong in a language. Rules like “never end a sentence with a preposition.” Prescriptivists are generally fighting a losing battle and spend most of their time bemoaning the decline of their language because people aren’t following the rules.

Language descriptivists work the exact opposite way. They see their job as documenting existing language usage instead of defining it. Lexicographers—like Merriam-Webster or the Oxford English Dictionary—receive complaints from angry prescriptivists when dictionaries document usage like “literally” meaning “figuratively”.

Dictionaries are descriptive, not prescriptive.

I’ve seen the prescriptive/descriptive divide somewhere else too. I’ve seen it in the world of design systems.

Jordan Moore talks about intentional and emergent design systems:

There appears to be two competing approaches in designing design systems.

An intentional design system. The flavour and framework may vary, but the approach generally consists of: design system first → design/build solutions.

An emergent design system. This approach is much closer to the user needs end of the scale by beginning with creative solutions before deriving patterns and systems (i.e the system emerges from real, coded scenarios).

An intentional design system is prescriptive. An emergent design system is descriptive.

I think we can learn from the worlds of web standards and dictionaries here. A prescriptive approach might give you a beautiful design system, but if it doesn’t reflect the actual product, it’s fiction. A descriptive approach might give a design system with imperfections and annoying flaws, but at least it will be accurate.

I think it’s more important for a design system to be accurate than beautiful.

As Matthew Ström says, you should start with the design system you already have:

Instead of drawing a whole new set of components, start with the components you already have in production. Document them meticulously. Create a single source of truth for design, warts and all.

Wednesday, June 26th, 2019

Phenological Mismatch - e-flux Architecture - e-flux

Over the last fifty years, we have come to recognize that the fuel of our civilizational expansion has become the main driver of our extinction, and that of many of the species we share the planet with. We are now coming to realize that is as true of our cognitive infrastructure. Something is out of sync, felt everywhere: something amiss in the temporal order, and it is as related to political and technological shifts, shifts in our own cognition and attention, as it is to climatic ones. To think clearly in such times requires an intersectional understanding of time itself, a way of thinking that escapes the cognitive traps, ancient and modern, into which we too easily fall. Because our technologies, the infrastructures we have built to escape our past, have turned instead to cancelling our future.

James writes beautifully about rates of change.

The greatest trick our utility-directed technologies have performed is to constantly pull us out of time: to distract us from the here and now, to treat time as a kind of fossil fuel which can be endlessly extracted in the service of a utopian future which never quite arrives. If information is the new oil, we are already, in the hyper-accelerated way of present things, well into the fracking age, with tremors shuddering through the landscape and the tap water on fire. But this is not enough; it will never be enough. We must be displaced utterly in time, caught up in endless imaginings of the future while endlessly neglecting the lessons and potential actions of the present moment.

Sunday, February 17th, 2019

The ineffectiveness of lonely icons | Matt Wilcox, Web Developer & Tinkerer

When in doubt, label your icons.

When not in doubt, you probably should be.