Kyle Hughes

@kyle@mister.computer
1,048 Followers
643 Following
7.4K Posts

I am a polite software developer and I am always committed to the bit. I will be your favorite app maker’s favorite app maker.

I am enamored by user-facing software, especially mobile, and especially iOS. Swift is my current weapon of choice but I will use any made-up word to solve any problem. I ship my side projects for free.

I run this single-user Mastodon instance in good faith and I intend to keep it that way.

pronounshe/him/his
websitehttps://kylehugh.es
githubhttps://github.com/kylehughes
threadshttps://www.threads.net/@kyle_hughes
Officially all moved in. Nothing else to do. Everything is where it should be.
I can’t wait for Google to announce AlphaRot, a system that uses RLHF to produce a nonstop stream of generated, personally-tailored, short-form video that is psychologically impossible to look away from.
Xcode 26 manages to catch up to Cursor circa June 2024 right when Cursor circa June 2025 is leapfrogged by Claude Code. There’s always next year!

I like this take by @kentbeck on how AI-assisted programming changes the balance of which skills are most important

From this interview with @gergelyorosz https://newsletter.pragmaticengineer.com/p/tdd-ai-agents-and-coding-with-kent

I hope I get deployed to LA and not Iran 🤞🏻
Dario Amodei was right: AI will be writing (or capable of writing) 90% of all code by August, and probably 100% by next year.
https://cosocial.ca/@timbray/114724388593141308
Tim Bray (@timbray@cosocial.ca)

So, @mitsuhiko@hachyderm.io is working on using LLMs to process XML Except for, the models can’t write legal XML. So he’s using the model to generate a sloppy-XML parser: https://lucumr.pocoo.org/2025/6/21/my-first-ai-library/ OK, my mind is now made up about vibe coding. I’m saying take the ship up and nuke the site from orbit. It’s the only way to be sure. #genAI

CoSocial
I have already made several of what I assume are common homeowner blunders where, by virtue of being in sticker shock over the cost of everything, I went with the cheapest option for every contractor and appliance and regret absolutely all of it.

This screen is why I had Rank Things on the shelf for years. I wanted a way to communicate the “user experience” of each sorting algorithm, because it meaningfully affects the app. For example, Insertion Sort has you compare one thing to many other things in sequence. That can be boring, but it can also keep you in the flow.

I’m not sure that I nailed it, but it’s good enough for government work. Plus, it uses the same stateful sorting algorithm implementations to drive the animation.

Does anyone know of a non-FDIC-insured place I can park my money? Oh, the Walmart Shitcoin? Perfect.

☺️ New* to me house ☺️

*built in 1965

×

I like this take by @kentbeck on how AI-assisted programming changes the balance of which skills are most important

From this interview with @gergelyorosz https://newsletter.pragmaticengineer.com/p/tdd-ai-agents-and-coding-with-kent

@simon @kentbeck @gergelyorosz There’s certainly something to it, but a real problem with AI assisted programming today is related to the old adage that if you write code as cleverly as you are capable of, you won’t be clever enough to debug it. AI-assisted programming hugely amplifies that challenge. Perhaps it goes away as the tools get better, but today it’s a problem.
@simon @kentbeck @gergelyorosz Do they discuss how people are going to acquire those 10% in the future (I assume those are the advanced seniority 10 percents?)

@helge @kentbeck @gergelyorosz that's one of the most interesting questions right now, I think

We clearly need to reimagine aspects of how we train new software engineers

@simon @helge @kentbeck @gergelyorosz my friend mentioned the other day we should also think about "training the AI". Should I publish books that are written for AI and not books written for people?
@chris @simon @kentbeck @gergelyorosz If you get paid for that, sure 🙂 I still think AI is a huge issue because of the "stealing" part (doesn't matter what you call it, but I think we all understand the issue and that it leads to content not being published anymore publicly).
It's essentially the other side of the seniority coin, if everyone just synthesises code, there is no new input for number 5.
@helge @chris @simon @kentbeck @gergelyorosz I'm sure that StackOverflow is a huge input for programming information, and I know I'm not alone in dramatically reducing my time there. After writing over 5700 answers over 15 years, I haven't answered anything in 2025. I do expect this to become an existential problem for the models across a lot of fields.
@helge @chris @simon @kentbeck @gergelyorosz But to Beck's point, I think to a first order, you should think of coding assistants like a higher-level programming language, not a complete reinvention of programming. I find that most of the usual skills still apply, even when they're running at their best. And to "how will junior devs learn the low level skills I know," I'd say the same way most devs learn assembly language. They don't. And it's mostly fine.
@helge @chris @simon @kentbeck @gergelyorosz My much bigger concern, having used coding assistants quite a bit now, is that they have the ability to really trash a code base really fast when they get confused, which is often. And I expect that this will be a major problem. I really like using them at the very start, but they tend to go off the rails pretty often, and I have to take control back. I expect that will give plenty of experience to junior devs.

@cocoaphony @chris @simon @kentbeck @gergelyorosz I actually think it is mostly the same issue, just at a much, much lower speed. Someone who knows assembly usually writes better code (not because she is older, but has a solid understanding of how things work internally, though admittedly that may be counter today).
But AI brings that issue (not understanding what happens) from an acceptable level to 100x.

Either way, I think it can be helpful to senior devs because they can rate the output.

@helge @chris @simon @kentbeck @gergelyorosz Of course when higher level languages were first developed, senior engineers did not feel that the issue was an acceptable level :D

I'm seeing some junior devs get in way over their heads following AI advice. (I'm kind of developing a stock lecture about it…) I'm also seeing junior-to-intermediate devs use AI to explore and learn deep things they wouldn't have dared before. I'm seeing the dig into details that before they'd have left as unknowable.

@helge @chris @simon @kentbeck @gergelyorosz (And yes, AI hallucinates. And also, when you research things on the internet, the internet hallucinates. And when you study things in books, they also sometimes are just flat wrong. There are definitely differences, but it is not a fundamental break with the past.

@cocoaphony @helge @chris @simon @kentbeck @gergelyorosz the difference (to my mind) is that if you have a solid foundation in “how things actually work”, you can design an experiment to figure out what is really happening so you don’t get misled. Absent that foundation … all you can do is hope.

That doesn’t have to mean “writing assembly,” but “knowing that there’s an actual spec and knowing how to read one” is an _invaluable_ skill that’s severely diluted by vibe coding. Even the idea of having a spec is diluted.

@steve @helge @chris @simon @kentbeck @gergelyorosz Also true. Though time and again I discover that how I think things actually work, based on my decades of foundations, is...huh, not actually how things work (which I learn when someone like Steve explains it to me... :D)

Certainly, learning foundations will always be valuable. But I remember my mentor in 1996 fussing that I shouldn't waste so much time digging into details. I think they were wrong. But it's not like *everyone* used to care.

@cocoaphony @helge @chris @simon @kentbeck @gergelyorosz The thing I worry about losing (and which we had already lost to some extent pre-wet-hot-AI-summer) isn't any specific skill or knowledge, but rather the common agreement that computer systems are deterministic things and you can figure out how anything works (or why it doesn't work) by a combination of deliberately reading a specification and conducting experiments to validate it.
@steve @helge @chris @simon @kentbeck @gergelyorosz But I am with you about "vibe coding." I expect that's a fairly short-lived thing. When I see people who are really successful with it, it turns out there was often a *lot* of planning that went into that "vibe." :D
@cocoaphony @steve @chris @simon @kentbeck @gergelyorosz I wouldn't underestimate that. It isn't that different to "regular" users hacking up Excel macros or say Shortcut scripts (which usually s*** from a dev pov, but they do the job). It is an enabler, and as long as the users can properly rate the output, that is kinda ok (seniority again).

@helge @steve @chris @simon @kentbeck @gergelyorosz Agreed that coding assistants are definitely lowering the bar (in a good way) for non-devs to build their own tools. I've seen quite a lot of that, and it's a great thing.

I think some folks are scaling that incorrectly to "AI, build and deploy a replacement for Netflix, I'll come back in an hour." This is very related to how folks confuse prototypes with "almost ready to ship."

@cocoaphony @chris @simon @kentbeck @gergelyorosz Of course that always was a thing. The level w/ AI is *way* higher, like 100x (or 1000x according to the article) vs like 2x or maybe 10x. Entirely different scale and problem domain.
Suggesting that this is just the regular "new abstraction" complaint is distracting from the broadness of the issue, IMO.

@simon @kentbeck @gergelyorosz I don't write code. I am more of an _idea_ person.

Good luck with that.

@lemgandi @simon @kentbeck @gergelyorosz If what you’re saying is that there’s not a lot of value in being an “ideas person”, i.e. someone who designs and architects code based projects, then I can see that too. Because just as LLMs have wowed people into thinking that the basic skills of programming are now pretty much worthless (as in the original quote), I have absolutely no doubt that in the next couple of years it will be possible to get good enough ideas-type work out of agentic AI as well. People will share their rule files and whatever other crap, and alongside enhanced context awareness it’ll be the same thing… so then where’s your value as a human programmer? Enjoy “talking” to an IDE all day long and nibbling at the edges of design decisions and code alike?

@jimgar @simon @kentbeck @gergelyorosz Ideas are very cheap. How 'bout a website where you can design a door? Or one that helps you find the best food for your dog? Or a site to help you fix your shoes? Or a phone app that will automatically order your lunch from the nearest fast food restaurant?

Implementation is hard. Writing a real application that can actually withstand malice is hard. Understanding the real world is hard.

@simon @kentbeck @gergelyorosz You are all programmers in this thread. I am not, but see how the quote of Simon’s original post is mostly applicable to general white collar work too. Lots of ”what is done” is just repeating patterns that have been robustly done before (thus - can be tackled/helped by LLMs), while a very small percentage of work (varies with personality and role) is applying judgement in context that is unique. (1/2)

That judgement needs to be practised while getting to grips with the fundamentals.

To every junior, the world is black and white (digital), while over most folks lifetimes shades of grey appear (analogue). (2/2)