suprfnk

Yep, it’s pretty much the reason I don’t use Youtube on my iPhone almost at all.

It’s probably a good thing, actually.

Need is a big word. Convenience is also a factor.

We have 8 light buttons in our living room/dining room/kitchen space. It is very convenient to us that we have 1 button for turning all of them on/off at the door to upstairs (at night turn off all lights and go to bed upstairs, in the morning come downstairs and turn on all lights) - but also have 1 on/off button near our back door for when we leave/come home.

Next to that: on/off toggles a schedule where the lights are bright and cold-ish by day, and low and warm by night without us having to manually adjust each light every hour or something.

Again, need is a big word. But it's very convenient and pleasant.

It's really not that bad.

Unless the company is going under, why not? Let's say Google releases Gemini Pro 4 tomorrow, and it's better than Fable and Sol; lots of people would switch over to it.

AI models are almost completely interchangeable, so the best/cheapest/fastest whatever will always have a market.

Way slow? What are you comparing with?

Definitely try ghostel, it's really solid.

Very well written! I haven't read such a long piece on the internet for quite a while but this hooked me immediately, and kept me hooked.

Breath of fresh air between all the AI """writing""".

> Even though it's 5 different phases, it's just "3 layers" of programming.

I'd sharpen this to: it's 3 layers of software engineering (2, 3, 4), and 1 layer of programming (3).

Seems like a good avenue for money laundering if you can't tell where it comes from.

It's really not that hard. There's a lot to learn, but it's doable.

Start here: https://docs.godotengine.org/en/stable/getting_started/intro...

Or if you're impatient like me you click "Your first 2D game" or "Your first 3D game" in the left bar (whichever you prefer) and go through that -- and skipping back to the intro/step by step when you don't understand something.

By the end of that you'll have made your first game.

From there you just do something extra to it. Mix it up. Start a new project with a different (small) idea. Build small projects until small becomes medium becomes large.

Just like learning anything else, really.

> you aren't really expected to talk or listen in this scenario

Absolutely bizarre. The cashier is not some sort of robot.

Interesting; do you think it’s a net positive for them?

Feels like they’re just surfing the name recognition wave at this point.

A lot, but these I still use a lot

A grocery app tailor made for me and my wife, offline first, seamless instant sync, barcode scanning, GPS/location hints

A macOS native high performance infinite canvas scribbling app for use with my Wacom for thinking through ideas

Lots of stuff for one pretty much finished video game, and currently lots of stuff for my new video game

Why should we say stop?

Agreed, these are my vibes too. It feels much better to do planning and strategy and architecture etc. with Opus 4.7 than GPT-5.5. GPT just feels like a robot that gets instructions and does exactly that. Opus feels like an almost human that sometimes has actually good ideas and pushes back on bad ideas.

So for now its planning/architecture/strategy -> Opus. Pure coding -> GPT.

Helps with agentic coding that GPT is much roomier with the tokens you get.

Oh, so that was actually a Token Per Second report! Wild!

I don't think they think. I still use them a lot despite that, because they are very powerful parameterised code generators.

> to start with a blank canvas and create something that others will value

AI is much faster at taking an idea and creating a working proof of concept than any human I've seen.

Not saying it's good engineering, but leave that to the gardeners.

But then, if an agent picks the best response, how would you know that that is reliable?

I also have a small private app that technically could have been a PWA.

It’s not a PWA because the UX is just always inferior. Even though we’ve come really far in browser UIs, the browser is still very clunky compared to the smoothness of a native app.

And I like nice to use software.

And if not losing, the battery dies in 2-3 years, so you'll have to buy new anyway.

No I can confirm this. I am at least an average C# dev, with 16 years of experience.

I have built a very nicely responsive real-time syncing iOS app in what amounts to a weekend of time. (I only have an hour here and there, young kids) I had zero iOS/Swift development experience prior to it.

I can also confirm that this wouldn't have been built if it weren't for Claude Code. It's "just" an improved groceries app, that works especially well for my wife and me.

Without LLM's, and with just an hour here and there, I wouldn't have done the work to learn the intricacies of iOS and Swift dev, set up the app, and actually tweak and polish it so it works well -- just to scratch the itch of a bit better groceries handling.

C# pays fine

“A human being should be able to change a diaper, plan an invasion, butcher a hog, conn a ship, design a building, write a sonnet, balance accounts, build a wall, set a bone, comfort the dying, take orders, give orders, cooperate, act alone, solve equations, analyze a new problem, pitch manure, program a computer, cook a tasty meal, fight efficiently, die gallantly. Specialization is for insects.”

― Robert A. Heinlein

A tiny bit of this is already here: our robot vacuum & mop vacuums and mops the living room, kitchen, and dining room every night at 01:00.

Coming downstairs in the morning to a completely clean floor is definitely a tiny bit of that magic.

I agree with the sentiment, but: how do you navigate? Especially to unknown places?

@wwilson How do you define the X/Y "distance" of a non-Mario application? I.e. any (distributed or not) system that doesn't have a relatively trivial "higher x/y is better" fitness function?

Being by far the most convenient way to travel from home to pretty much any random location.

Speaking from the Netherlands with a relatively good public transit system.

This is a pretty short-sighted take. VR just doesn't offer much of anything currently. Some games work well, but most games are pretty clunky. Office work isn't substantially improved. A big warm sweaty headset is not nice to have on your head for extended amounts of time.

There's a plethora of reasons why VR in its current state is little more than a gimmick.