> If your idea generation isn’t outpacing your implementation speed

For me, it definitely is. Hell, my idea generation outpaces my ability to delegate it to agents. I can't do all the things I want to do because I don't have enough time in the day to vocalise them all, let alone hand code.

But in my case, I choose to handcode sometimes because I value the certainty of the results more than the speed of development.

It's the choice between a well-engineered application that does a handful of things reliably through a well-tested UI, or a rough-around-the-edges app that does 50 different things passably well, most of the time, with an inconsistent UI and lots of small bugs

People here might question the "lots of small bugs" but I have developed some apps solely with LLMs and despite using test-suites and spec-driven development I still face constant regression and UI bugs creeping in with every revision.

A good example - in React Native, in Android, Claude cannot keep the controls above where the onscreen nav appears, no matter how many times I ask it to. It'll solve it until three iterations later when the issue will return on another screen.

I don't think anyone chooses to relinquish all control from a project they've worked hard on. It's a slippery slope. You start with allowing it to help out a tiny bit, being in control and understanding the code the LLM writes, and then you become more confident in the results, and you trust it, and you don't read every line, and before long its refactoring an entire file by itself and you're not reading it.

And then you look up one day and you don't recognise the codebase

I'm able to avoid slipping down that slope, just don't be lazy. If you look up one day and don't recognize the codebase that's because you haven't actually looked at it in a long time. Obviously when you don't pay attention you miss things. Just pay attention, it's not hard. There's plenty of time for it while Claude or whatever is working through stuff for you.

It's worse than that, someone else generated it using and then put it on a static page. We just have to take their word for it that GPT6 can do this. It probably can. It's not really an impressive test anymore. Claude Fable can do it. Opus can do it. I've been making one-shotted games with models for a while now, to test out their capabilities, and they all pretty much come out like this - generic bland and basic, using three.js with rudimentary controls and zero gameplay other than collecting points.

Here's a one-shotted submarine game I made with Fable a few weeks back - https://roryok.com/games/deepdive3d.html. One prompt, and I think it's deeper than this (if you'll pardon the pun)

Interesting concept, but the controls disappeared after a few seconds and I still hadn't read all of them

well, its a one prompt POS so I'm not surprised

I love your game. It's wonderful and exactly the sort of thing that would showcase something interesting as opposed to just copying what's already out there. It is something I could share with my kids, and exactly the right note of fun and exploratory in a unique and even natural way. It could be extended and played with.

I usually roll my eyes when I see a comment like this because rarely do they make the points they claim to make, but I see what you're getting at. They just chose to clone someone elses work and do it in a boring way. I like OpenAI's models a lot, but they should do better.

edit - just a sidenote that I hadn't looked at the games, I just took the comment about "super-mario cart" at face value. I stand by my points 110% (even moreso perhaps), what they're showing is more polished than I expected, I assume they spent a lot of tokens on it. It is a legit shame they couldn't have spent time thinking of a better idea to illustrate something just as polished, but more interesting.

Thanks. But even my game is a piece of shit. It shows LLMs can make a working 3d world start to finish from a single prompt, but with no soul. I wasn't excited to play it anymore than I was excited to play the shitty mariokart clone (that you don't even need to turn for)

LLMs produce games that look right but feel all wrong, because they're generalising and imitating. This is also why AI video tools can make an astonishingly authentic looking "GTA 5-but in Roman Times" or whatever, but they couldn't conjure up anything original. Only imitations of what people have already thought up.

By their very nature, they predict from a large set of data what the most likely thing is, and as humans, we crave the less likely thing.

My submarine game is generic tripe. Sure, it checks the boxes of what I asked for. You explore an undersea world in a tiny sub. Hooray. LLMs can build this kind of thing that nobody wants to play in minutes. But if you asked LLMs to make a thousand different undersea games you'd never get Dave The Diver, or Barotrauma, or Subnautica, or Sunless Sea, or Aquanox. You'd just get something that looks like it was released for Kinect but never charted.

You sound like an AI.

Funny since no, but I really did like it and for those reasons. Don’t see a lot of post first comment edits anymore, so I’ve got that going for me.

$20k seems steep for whats effectively a small shed with a nice finish. Especially that the bare shed itself was $6k. In Ireland I can get an 18x10ft cabin for about €5k, and this is one of the most expensive countries

West coast prices are in a different ballpark. Im shocked at how cheap the concrete work was. I got 20 quotes and 6k was the cheapest for a 12x12 pour.

I have a neighbor 100k+ into a foundation retrofit for his living room.

morbid question, but do you know if any emails have ever been sent?

Of course, lots are sent every day. I don't know if they're from deaths, but lots of messages get sent. I know people have died because the police or FBI contact me sometimes.

Once, a girl had committed suicide and used the service to send accusing emails to her friends and family two months later. That was tragic all around.

There’s probably some selection bias here if people are close to death (either by suicide or terminal diagnosis) and looking for the solution.

Pretty neat but a talking dog is so weird, especially one that sounds like Stellan Skaarsgard

Would be better if he just barked

Im recently intrigued by Solo Flight, although I havent played it yet. The idea of taking that military flight sim base and just turning it into a casual flying-for-fun game is something that resonates with me. I did love Flight Unlimited which is an obvious spiritual successor

They worked on one thing forever

While I agree with the sentiment it seems unnecessary for things like this to have their own domain name. Surely a blog post would cover this?

I'm also working on an N64 style cozy flight game, but not over seattle. Also I am far less further along than you