So instead of asking yourself, “How can I write code that does what I want?” Consider asking yourself, “Can I write code that ties together things the browser already does to accomplish what I want (or close enough to it)?”
It’s wild what you can do with CSS these days!
A URL shortener that’s dodgy by design.
A great interview with Ted Chiang:
Predicting the most likely next word is different from having correct information about the world, which is why LLMs are not a reliable way to get the answers to questions, and I don’t think there is good evidence to suggest that they will become reliable. Over the past couple of years, there have been some papers published suggesting that training LLMs on more data and throwing more processing power at the problem provides diminishing returns in terms of performance. They can get better at reproducing patterns found online, but they don’t become capable of actual reasoning; it seems that the problem is fundamental to their architecture. And you can bolt tools onto the side of an LLM, like giving it a calculator it can use when you ask it a math problem, or giving it access to a search engine when you want up-to-date information, but putting reliable tools under the control of an unreliable program is not enough to make the controlling program reliable. I think we will need a different approach if we want a truly reliable question answerer.
Adios, Cáceres!
A nifty interactive 3D map of our solar system
When you vibe code, you are incurring tech debt as fast as the LLM can spit it out. Which is why vibe coding is perfect for prototypes and throwaway projects: It’s only legacy code if you have to maintain it!
The worst possible situation is to have a non-programmer vibe code a large project that they intend to maintain. This would be the equivalent of giving a credit card to a child without first explaining the concept of debt.
If you don’t understand the code, your only recourse is to ask AI to fix it for you, which is like paying off credit card debt with another credit card.
Find freedom not in infinite choice, but in working a single seam until you strike gold: conducting dozens, even hundreds, of iterations within a tight parameter space—not in search of more, but in search of better.
CSI London, York, and Oxford:
Discover the murders, sudden deaths, sanctuary churches, and prisons of three thriving medieval cities.
This page collects my blog posts on the topic of fighting off spam bots, search engine spiders and other non-humans wasting the precious resources we have on Earth.
The short version of what I want to say is: vibe coding seems to live very squarely in the land of prototypes and toys. Promoting software that’s been built entirely using this method would be akin to sending a hacked weekend prototype to production and expecting it to be stable.
Remy is taking a very sensible approach here:
I’ve used it myself to solve really bespoke problems where the user count is one.
Would I put this out to production: absolutely not.
The joy came flooding back to me! It turns out browser APIs are really good now.
I don’t use large language models. My objection to using them is ethical. I know how the sausage is made.
I wanted to clarify that. I’m not rejecting large language models because they’re useless. They can absolutely be useful. I just don’t think the usefulness outweighs the ethical issues in how they’re trained.
Molly White came to the same conclusion:
The benefits, though extant, seem to pale in comparison to the costs.
What I do know is that I find LLMs useful on occasion, but every time I use one I die a little inside.
I genuinely look forward to being able to use a large language model with a clear conscience. Such a model would need to be trained ethically. When we get a free-range organic large language model I’ll be the first in line to use it. Until then, I’ll abstain. Remember:
You don’t get companies to change their behaviour by rewarding them for it. If you really want better behaviour from the purveyors of generative tools, you should be boycotting the current offerings.
Still, in anticipation of an ethical large language model someday becoming reality, I think it’s good for me to have an understanding of which tasks these tools are good at.
Prototyping seems like a good use case. My general attitude to prototyping is the exact opposite to my attitude to production code; use absolutely any tool you want and prioritise speed over quality.
When it comes to coding in general, I think Laurie is really onto something when he says:
Is what you’re doing taking a large amount of text and asking the LLM to convert it into a smaller amount of text? Then it’s probably going to be great at it. If you’re asking it to convert into a roughly equal amount of text it will be so-so. If you’re asking it to create more text than you gave it, forget about it.
In other words, despite what the hype says, these tools are far better at transforming than they are at generating.
Iris Meredith goes deeper into this distinction between transformative and compositional work:
Compositionality relies (among other things) on two core values or functions: choice and precision, both of which are antithetical to LLM functioning.
My own take on this is that transformative work is often the drudge work—take this data dump and convert it to some other format; take this mock-up and make a disposable prototype. I want my tools to help me with that.
But compositional work that relies on judgement, taste, and choice? Not only would I not use a large language model for that, it’s exactly the kind of work that I don’t want to automate away.
Transformative work is done with broad brushstrokes. Compositional work is done with a scalpel.
Large language models are big messy brushes, not scalpels.
Here’s some code to show the distance to the nearest airports on a map.
Here’s a modified version that shows the distance to the nearest Gregg’s. The hub-and-spoke visualisation overlaid on the map changes as you pan around, making it look like a spider bestriding the landscape.
Jonty’s version shows the distance to the nearest Pret a Manger.
I got nerdsniped by someone saying:
@adactio This would be cool for sessions 😉
He’s right, dammit! So here you go:
Now you can see how far you are from the nearest traditional Irish music sessions.
It’s using data from the weekly data dumps from thesession.org—I added a GeoJSON file in there.
Pure silliness, but it does make me wonder what kind of actually good data visualisations could be made with all this scrumptious data.
Here is the state of venture capital in early 2025:
- Venture capital is moribund except AI.
- AI is moribund except OpenAI.
- OpenAI is a weird scam that wants to burn money so fast it summons AI God.
- Nobody can cash out.
The Wikimedia Foundation, stewards of the finest projects on the web, have written about the hammering their servers are taking from the scraping bots that feed large language models.
Our infrastructure is built to sustain sudden traffic spikes from humans during high-interest events, but the amount of traffic generated by scraper bots is unprecedented and presents growing risks and costs.
Drew DeVault puts it more bluntly, saying Please stop externalizing your costs directly into my face:
Over the past few months, instead of working on our priorities at SourceHut, I have spent anywhere from 20-100% of my time in any given week mitigating hyper-aggressive LLM crawlers at scale.
And no, a robots.txt file doesn’t help.
If you think these crawlers respect robots.txt then you are several assumptions of good faith removed from reality. These bots crawl everything they can find, robots.txt be damned.
Free and open source projects are particularly vulnerable. FOSS infrastructure is under attack by AI companies:
LLM scrapers are taking down FOSS projects’ infrastructure, and it’s getting worse.
You try to do the right thing by making knowledge and tools freely available. This is how you get repaid. AI bots are destroying Open Access:
There’s a war going on on the Internet. AI companies with billions to burn are hard at work destroying the websites of libraries, archives, non-profit organizations, and scholarly publishers, anyone who is working to make quality information universally available on the internet.
My own experience with The Session bears this out.
Ars Technica has a piece on this: Open source devs say AI crawlers dominate traffic, forcing blocks on entire countries .
So does MIT Technology Review: AI crawler wars threaten to make the web more closed for everyone.
When we talk about the unfair practices and harm done by training large language models, we usually talk about it in the past tense: how they were trained on other people’s creative work without permission. But this is an ongoing problem that’s just getting worse.
The worst of the internet is continuously attacking the best of the internet. This is a distributed denial of service attack on the good parts of the World Wide Web.
If you’re using the products powered by these attacks, you’re part of the problem. Don’t pretend it’s cute to ask ChatGPT for something. Don’t pretend it’s somehow being technologically open-minded to continuously search for nails to hit with the latest “AI” hammers.
If you’re going to use generative tools powered by large language models, don’t pretend you don’t know how your sausage is made.
Heydon is employing a different tactic to what I’m doing to sabotage large language model crawlers. These bots don’t respect the nofollow rel value …so now they pay the price.
Raising my own middle finger to LLM manufacturers will achieve little on its own. If doing this even works at all. But if lots of writers put something similar in place, I wonder what the effect would be. Maybe we would start seeing more—and more obvious—gibberish emerging in generative AI output. Perhaps LLM owners would start to think twice about disrespecting the
nofollowprotocol.
I really like the idea of unifying some layout values in CSS. If you’ve got any feedback, please chip in!
As it currently stands, both the rapid growth of AI-generated content overwhelming online spaces and aggressive web-crawling practices by AI firms threaten the sustainability of essential online resources. The current approach taken by some large AI companies—extracting vast amounts of data from open-source projects without clear consent or compensation—risks severely damaging the very digital ecosystem on which these AI models depend.
AI companies with billions to burn are hard at work destroying the websites of libraries, archives, non-profit organizations, and scholarly publishers, anyone who is working to make quality information universally available on the internet.