arkensaw

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

> 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

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.

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)

$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

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

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

the only thing they sell for anything close to that price is a pair of earphones for $99.

https://electronics.sony.com/audio/walkman-digital-recorders...

The cheapest walkman model is $399.99

to kids today a dead channel would likely mean a youtube channel with no posts for a few years

> "I was born in the City of Bombay… once upon a time." > Midnight's Children > Salman Rushdie · 1981

Ok so I guess it is literally just openings of famous literary works, and not great first lines

Its a genuinely nice idea, I do love the second clock face you've done, the sort of "fuel gauge" one. I think a great next step would be some sort of gallery of clock faces that people can use and contribute to, based on whatever code you've used to create them

space is very large but low earth orbit is not.

I feel obliged to point out Stanslav Petrov, who absolutely got credit for fixing a problem that never happened. Granted it's a very extreme case.

They released it, and look what happened. It WAS too dangerous.

Chrome takes up a few gigs on windows for no good reason anyway, mostly caching of websites you went to one time

> You have been on this page for 92 seconds. You scrolled 0% of the way down. You never left this tab.

Uhm... how did I get to the bottom if I scrolled 0%?

maybe not great naming. Sounds very similar to the rapper D4vd, who was just arrested for murdering a 14 year old girl

maybe I'm being dense, but why do people keep reinventing markdown to make it more like HTML when HTML exists?

> No Vibe Coding. Classic development style.

This is fast becoming a feature people want.

no AI could ever be so poetic. nice

hah, no, not even a bit.

I am not. But I guess I'd fit right in. If I could speak German

> In Germany, people complain when the train is late. Everywhere else, the train is just late.

You think people don't complain when the train is late in other countries? That's hardly a uniquely German thing

I am German, not autistic.

This confuses me as I have never been to Germany and do not speak German.

But rules are rules.

fun fact: voice typing also worked excellently on Windows Phone, although only in the SMS app

> This class of bug seems to be in the harness, not in the model itself. It’s somehow labelling internal reasoning messages as coming from the user, which is why the model is so confident that “No, you said that.”

from the article.

I don't think the evidence supports this. It's not mislabelling things, it's fabricating things the user said. That's not part of reasoning.