It looks like it will be a great tool for prototyping. A tool to help developers that don’t have experience with CSS and layout to have a starting point. As someone who spent some time building smoke and mirrors prototypes for UX research, I welcome tools like this.
What concerns me is the assertion that this is production-grade code when it simply is not.
Another great talk from Simon that explains large language models in a hype-free way.
Time capsules on the moon, using NanoFiche as the storage medium.
As part of this pointless push, an “AI explain” button appeared on MDN articles. This terrible idea actually got pushed to production (bypassing the usual deploy steps) where it lasted less than a day.
You can read the havoc it wreaked in the short term. We’ll find out how much long-term damage it has done to trust in Mozilla and MDN.
This may be the worst use of a large language model I’ve seen since synthentic users (if you click that link, no it’s not a joke: “user research without the users” is what they’re actually proposing).
Ingesting every piece of art ever into a machine which lovelessly boils them down to some approximated median result isn’t artistic expression. It may be a neat parlour trick, a fun novelty, but an AI is only able to produce semi-convincing knock-offs of our creations precisely because real, actual people once had the thought, skill and will to create them.
In some ways, the fervor around AI is reminiscent of blockchain hype, which has steadily cooled since its 2021 peak. In almost all cases, blockchain technology serves no purpose but to make software slower, more difficult to fix, and a bigger target for scammers. AI isn’t nearly as frivolous—it has several novel use cases—but many are rightly wary of the resemblance. And there are concerns to be had; AI bears the deceptive appearance of a free lunch and, predictably, has non-obvious downsides that some founders and VCs will insist on learning the hard way.
This is a good level-headed overview of how generative language model tools work.
If something can be reduced to patterns, however elaborate they may be, AI can probably mimic it. That’s what AI does. That’s the whole story.
There’s very practical advice on deciding where and when these tools make sense:
The sweet spot for AI is a context where its choices are limited, transparent, and safe. We should be giving it an API, not an output box.
I don’t agree with all of these takes-of-varying-spiciness, but Rich Harris is always worth paying attention to.
Every day, a new marketing email, Medium post, or VC who will leave Twitter when they’re cold in a body bag tells us that machine learning (ML, which they call AI because it sounds more expensive) is going to change the way we work. Doesn’t really matter what your job is. ML is going to read, write, code, and paint for us.
Naturally, the excitement around ML has found its way into the design systems community. There’s an apparent natural synergy between ML and design systems. Design systems practitioners are tantalized by the promise of even greater efficiency and scale. We wish a machine would write our docs for us.
We are all, every single one of us, huge fucking nerds.
I’ve been using Copilot for over a year now, and this is more or less how I use it: To help me quickly blast through boilerplate code so I can more quickly get to the tricky bits.
There’s a more subtle problem with ChatGPT’s code generation, which is that it suffers from ChatGPT’s general “bullshit” problem.
Paul’s indie web project is live!
Meet the little Node.js server with all the parts needed to publish content to your personal website and share it on social networks.
You can read the accompanying blog post.
View source on this bit of tongue-in-cheek fun from Terence.
This extract from Baldur’s new book is particularly timely in light of the twipocalypse.
I love not feeling bound to any particular social network. This website, my website, is the one true home for all the stuff I’ve felt compelled to write down or point a camera at over the years. When a social network disappears, goes out of fashion or becomes inhospitable, I can happily move on with little anguish.
A beautiful meditation on Christopher Alexander by Claire L. Evans.
New from Mr. Vanilla JS himself, Chris Ferdinandi:
A learning space for people who hate the complexity of modern web development.
It’ll be $29 a month or $299 a year (giving you two months worth for free).
A new programming language where you pray to Greek gods.
An invocation has three parts: the god’s name and adoration (praising of that god), supplication to show the humbleness of the asker, followed by a request to add one or several of what we ordinarily call “commands” to the program.
Here’s the source code for “99 bottles of beer” in Olympus and here it is transpiled into JavaScript.
If only all thinkpieces on complexity in software development were written in such an entertaining style! (Although, admittedly, that would get very old very fast.)
A layman’s guide to thinking like the self-aware smol brained
I love these notes on my recent talk!
A typeface co-designed with a tree over the course of five years.
Yes, a tree.
Occlusion Grotesque is an experimental typeface that is carved into the bark of a tree. As the tree grows, it deforms the letters and outputs new design variations, that are captured annually.
Write about what you learn. It pushes you to understand topics better. Sometimes the gaps in your knowledge only become clear when you try explaining things to others. It’s OK if no one reads what you write. You get a lot out of just doing it for you.
Lots of good advice from Addy:
Saying no is better than overcommitting.