danielvaughn

When I said that the world is more complex than that, I meant that she oversimplified it. To say that the opposite has happened is also an oversimplification.

From what I can remember (of reading the book 25 years ago), it predicted an increasing suspicion and resentment of excellence and competence, coinciding with a rise in socialist sentiments. The net result is that various aspects of society would begin to break down as the total amount of competence in the culture vanishes.

I think she attributed too much of the symptoms merely to socialism; obviously the world is more complex than that. But we've got this train crash, the ongoing issues with Boeing airplanes, several multi-billion dollar public infrastructure projects across America that have stalled and will likely never be completed (like the California high speed rail system), the list goes on.

Ayn Rand gets a lot of hate from the philosophy world, and Atlas Shrugged is definitely not a good novel by any means, but you have to give her credit for basically predicting where we are now from way back in the 50's.

By localizing basic style information and reducing the amount of weird CSS you have to write, you have thus reduced your keystrokes per style. We're talking about the same thing.

Agree the market is weird right now, but on that specific example - TailwindCSS was built around the notion of reducing keystrokes per style (basically). That's not as useful in the age of AI, of course. CSS-Tricks is about learning what modern CSS can do, which is arguably still useful. An uphill battle, for sure, but I think there's still a place for hand written human content on the web, so I plan to support it even if it's just with my clicks.

Very interesting. I think a useful experiment would be to show AI a photograph, then ask it to paint it or draw it.

I was 12 in 96 when I got my first computer - wow does this bring back memories.

For a while I was working on a browser for UI designers, which involved pretty heavy use of LLMs talking to CDP. In my experience, CDP is extremely token consumptive.

Haven't released it yet, but a little website for evaluating AI UI design. They're not actual evals, it's moreso just showing the results of different UI tasks across models, reasoning levels, skills, harnesses, etc.

Right. The only way I'd feel comfortable doing that is if I spent an inordinate amount of time writing very detailed specs, so in terms of labor offset I'm not sure the juice would even be worth the squeeze there. In other words, a sufficiently detailed spec is nearly indistinguishable from code.

What people seem to be wanting is for an agent to infer vast complex data from terse simple data, which I think is probably impossible on a philosophical level. There's real information loss in language, and compute can only make guesses at the end of the day. I really don't see how we bridge that gap.

Yes. I use these models day in and day out, on all sorts of tasks. I cannot believe I hear people say that coding is solved.

I've always loved Tailwind, but at this point I'm not exactly sure why Shopify acquired them.

I had a different experience.

I bought it on day one in 2016, and like everyone else, I was wowed by the planet hopping experience for about an hour or so. Then I put it down and didn't think about it again.

Then I picked it up a few years later, and discovered base building. Had more fun than the first playthrough, but it didn't click. Eventually I hear about something called the Galactic Hub, which is a star system marked by players as a central spot to build their bases. Kind of like a human home in the vast empty universe of NMS.

I get curious about it, and look up instructions on how to get there. I did some quick napkin math and realized it would take literally dozens of hours of grinding - nonstop travel - to get there. However, as it turns out, there's a loophole with black holes. When you enter a black hole, it spits you out into a totally different place in the galaxy. From the players perspective its random, but players got together and figured out that each unique black hole always sends you to the same spot in the galaxy. So they constructed a black hole "highway", along with an app that let you input your desired coordinates, and it would give you the list of black holes that would most optimally get you near your destination.

So I spend an evening playing the game, switching back and forth from the game to my laptop, inputting coordinates and slowly making my way closer and closer to the hub. Eventually I find it, and what was amazing was that it was the first time I'd seen any evidence of another player in the game.

That moment felt utterly magical, because while I was playing a game, I had an actual, real objective that I formed entirely on my own.

So yes, the game is an odd duck, but it can really open up with the right mindset.

Art is a social activity whereby a human uses their creativity to produce an artifact that expresses some aspect of their experience, using non-standard forms of communication. It's a way of signaling to others "do you see what I see? do you feel what I feel?" The beauty of art exists on two layers: the aesthetic quality of the work, and the sense of shared experience among those who consume the art.

We find aesthetic beauty in nature; we do not find artistry.

"We assume creative writing requires uniquely human qualities, such as emotional understanding and lived experience, which leads people to underestimate AI's capabilities."

It's not about the relative "creativity" of it. Art is fundamentally about communication. It's a social activity, whether you're reading a book or listening to music or looking at a painting. Even a mid-average author is going to make something more compelling, on a human level, than extraordinary prose generated by a machine.

AI-generated creative artifacts are as interesting as the fractals in a snowflake. Interesting, sometimes beautiful, but void of human meaning.

The most interesting creative decisions happen within a tight set of constraints.

Side note, I also had to expand my definition of "creativity" early in my career. I grew up and was educated as an artist. Even received a Bachelor of Fine Art Painting. Never took a single class on anything to do with computer science. As I was transitioning my career towards programming, I was worried that I would lose my creativity. It took me a while to realize that programming was intensely creative, just as much as being an artist. They simply have different aesthetics.

I've been on this kick for a long time. A few years ago I was exploring a UI design tool that was entirely keyboard-driven, using pneumonic keychords inspired by Vim: https://github.com/danielvaughn/stride

My experience is that while it's awesome to have really deep keyboard-driven experience, it can't _only_ be that. You need some graphical controls to help guide users.

To be fair, the article doesn't say that AC is banned - it mostly focuses on the HOA-style local ordinances and permits that discourage people from using AC.

I know someone who works at a data center for the IRS, and a lot of their records are all stored in PDFs. He thought it was disgusting when he first learned about it, but eventually realized that it's essentially resistant to a large scale data leak. Retrieval just isn't fast enough.

Some variant of this idea has played in the back of my mind over the last few years. I'd love to play Skyrim, but where each character builds their own context for their history, their personality, their goals, and their interactions with you. The world would feel incredibly alive.

The rest of the blog post doesn't strike me as AI generated. Hard to tell, and personally I think "hard to tell" is about as good as it's going to get from here on out, so I give the author the benefit of my doubt.

Agree that using AI for writing is a habit we collectively need to drop immediately.

For software within a certain complexity scope, this is true. Like the average SaaS CRUD experience that many web developers were building before AI - a lot of that can be handled almost entirely by agents, with very little human in the loop activity. But past a certain point of scale/complexity, this breaks down rapidly. In the past 8 months I've seen this occur several times, and if you only rely on agents to get you to that point, then you're in a heap of trouble when you do reach it, because it's very hard to backtrack.

Yes, human imperfection is and will always be an issue. I think humans should get out of the loop for finite tasks, but the problem specifically with software creation is that it's inherently unbounded. You need a human somewhere to reign it in and ensure it's aligned with intent.

A good example of a finite task is like something we're working on at my company. We're building a multi-agent orchestration engine for large scale offensive network ops. Think like an Active Directory attack. This kind of thing is extremely complex, and involves lots of ambiguity and cross-referencing. You couldn't deterministically program a machine to do this attack, but you could definitely coordinate a bunch of agents to work together to do it. And you don't need a human in the loop outside of some lightweight scoping and gating procedures.

That's definitely the goal. If the pseudocode is only ever touched by humans, then it will act as a frame of reference that could keep the LLM generated code in check.

Fascinating! I haven't been in the industry as long as you, but I can empathize with the sense of obsoletion. I was working on a design tool for over 10 years, with a goal of building a coding language that was understandable by designers. Once I tried ChatGPT for the first time back in 2021, I knew immediately that it was game over. All my work had gone down the drain.

For a while people were talking about the necessity of UBI in response to the potential elimination of jobs. I tend to take your view (I think it's your view) that it's more worthwhile to automate our basic necessities. Food, water, shelter - use technology to drive those costs down to zero or near zero so that an economically risky solution like UBI doesn't even need to be proposed.

In practice I think a lot of engineers would do this. My recommendation would be to avoid this at all costs. In my opinion, the way to scale a codebase with AI is to have some part of the codebase that is reserved only for human hands. You need to be able to look at something written, and to know that it expresses human intent. Once you deviate from that constraint, then you might be even worse off than before, because now you have 2 sets of generated source code to sift through, not 1.

Agree; something got lost in the sauce when we moved to the terminal.

Not yet, it's still a proof of concept. The next iteration will be a desktop app with filesystem access, so I'll be able to test out that scenario, as well as a few others.

We'd end up back where we started. One reason code is slow and expensive is that programmers have to tailor the syntax to precisely satisfy the compiler. The benefit of pseudocode is that you can choose how precise or imprecise you want to express your intent.

Yeah for sure. I think I made a mistake in neglecting to mention the core differentiator in this editor, which is that it maintains a source map from your pseudocode to the generate source. So as a codebase grows, you'll be able to point to the exact lines of your written prompt for any given line in the codebase. This way it acts as a frame of reference, for both agents and humans.