FredrikNoren

Wow that's great! Thank you!

Thanks! That's really interesting stuff, will definitely look into those!

I'm experimenting with an AI assisted world building / story telling tool: https://youtu.be/OGkSI3VfxRU . The idea is to do kind of what Cursor is doing for programming; accelerate the creative process (rather than replacing it).

So... I think maybe the same could have been said about writing once upon a time. "What if everyone could write, we'd flood the market with poorly written books!". Well we went from no one being able to write to almost everyone being able to. But just because everyone can technically write, it doesn't mean that everyone is a _writer_.

I believe that the same goes for AI tools for games. Yes, more people will technically be able to produce games. But I think that will shift the focus; it won't be enough with an impressive tech demo in the future, instead you have to connect to the human side of people when you build games.

We now see it as a natural thing that everyone can read and write. We don't want to go back to a time where it was only for a select few elites. If we turn things around and imagine that the technology exists that makes it possible for anyone to build games; then should we keep that from them? In that world, why would we want to gate keep game creation to only people that have time and money to go to a game school or equivalent? You might think "well everyone can learn on their free time", but that's not necessarily true.

I think we will see more human, and more personal experiences that touch us deeper, because they no longer can just be about the technology (since the technology will be commoditized). That's what I'm personally excited about and why I think it makes sense to work on this.

I do agree thought that it can feel overwhelming to look at all this in aggregate. There are already hundreds of thousands of games, why do we need more? But maybe looking at things in aggregate is not the right way to look at it. There have been countless conversations between people throughout history. Does that mean that a conversation is meaningless? I don't think so, and I think (some types of) games will move into this space too; something more personal, something we don't count in aggregate, something that is between maybe smaller groups of people, but more meaningful to those groups of people. At least that's something I'd be excited to see.

Nope, that's unrelated.

So it's hard to give a number on how robust it is, but yes, simply telling GPT that "this doesn't work" or "try again" does work a lot of the time. We're trying to give GPT as much context as possible to help it figure out where things went wrong. Currently that means giving it type errors, execution errors, self-critique and user feedback. But we're working on expanding that; for instance we want to experiment with automatically generating tests that validate things are working as they should. We also want to add a GPT based "debugger" that can help you pinpoint exactly what went wrong.

Thanks! We're using a service called Meshy (https://www.meshy.ai) to generate 3d models.

Thank you!

I'd say it's something in that direction (GameMaker) yeah. One big difference (other than the AI part) is that both building and playing is multiplayer by default. (Though of course, you can choose to make things single player and to build solo). With biting the hand that feeds it; I sure hope not! :) I've built my fare share of obscure indie games, and we in the company have friends and family members who do now as well, so the aim is to build something that can help people like this.

We haven't looked into exactly how this will be handled yet, but I believe this would fall under the same laws and restrictions as any other online platform (YouTube, TikTok etc.), it's just that the production tools are different.

Thanks! Oh yeah that would be really interesting to explore! We haven't done much with LLMs on the play side yet, but we know that there's so much that can be done there, that can open up for totally new types of games.

So far we've focused 100% on the creation side of things, but we're absolutely interested in helping people on the marketing side too.

Something we've discussed here is; since it's an online platform, could it be possible for creators to form communities around their games as they are being built (even more than now), with perhaps features to engage your community around what you create (imagine that your players can comment on things in the game as they play test it, for instance). This is quite speculative for now, but it's something we're interested in exploring.

Hi HN. We want to make it possible for anyone to build games without first learning to code or make art, by giving them access to an “AI game studio”. It’s early days, but here’s what we’ve learned so far building this product. Would love to hear what everyone thinks, and see if we can find some alpha testers for this!

Well, only a few people have tried it out so around $30 so far (haven't checked exactly how many but less than 30). The prompting is very unoptimized as well, so I'm sure it's possible to get that down.

Hm yeah I can see your project; it looks like the players were created outside of the map. If you click-drag the map a bit you'll see them in the lower right corner.

I'll see if I can give it a better understanding of the size of the map.

Thanks for detailed feedback!

So we view the browser as one distribution channel among many. We want Ambient to run everywhere. The first platforms we built out Ambient for were actually desktop native, we've since then also added the web support.

That said, we do believe that the web _is_ changing, and that it's becoming more and more viable that one day we'll see big hit games actually played through the browser, for one simple reason; sending a link to someone where they can jump in and start playing with you immediately is a very powerful interaction (not having to wait for downloads etc.). And there are fundamental technological shifts that are making this more and more possible; WebGPU is opening up for more advanced graphics, WASM is making it possible to run near-native code, and WebTransport is making it possible to run more high-demand netcode in games. We're building Ambient on top of all those three, and while it's early days still, we're really excited to see what people can accomplish with them!

Oh yeah, absolutely agree, we're not stopping at 60 ms. Client side prediction is planned (see Philpax answer https://news.ycombinator.com/item?id=37767359 and our netcode roadmap: https://github.com/AmbientRun/Ambient/issues/671).

Hm yeah, we need to fix the detection as part of instantiation, which happens in the engine. I'm adding a "Try anyway" button for you in the meantime, it should be up in a couple of minutes.

Yeah, it's part of the problem, but that would normally only give you ~60 - 100 ms lag (at least if you're on a decent connection, close-ish to the server). But we're experiencing another bug where WebTransport doesn't get a chance to send/receive data when the framerate is < 60fps (because the thread is starved), which makes it much worse than that. We're aware of it and working on it. This is the core issue: https://github.com/w3c/webtransport/issues/543

So if you browse to any game on you should see a download button to the left. Sorry to hear that the website doesn't feel good! Which parts of it specifically are you referring to?

It's built on top of WebTransport, which is also quite new. But yeah, we're also seeing the input lag issue here and we're on it, will be fixed soon!

When it comes to loading resources ahead of time: this is something devs can choose per-game (i.e. show loading screen or not), but yeah you might be right that it would be better for the examples we have to show a loading screen instead.

Pros: It's basically just a more modern API, so we can do a lot more (compute shaders for instance). There's a lot we can do on the performance side with it to make it faster than what we could do with WebGL. Cons: It's not yet available on all browsers unfortunately.

It's fixed on the website now as well (it'll show you a nice warning screen on non-webgpu browsers, instead of just loading forever)

Which version of chromium are you on? WebGPU is really new so it may require a browser update.

Haha indeed :)

We're actually only three full time devs :) But we're hiring! See the careers section on the website.

Hi, Ambient CPTO here; We're using wgpu (a rust crate), which supports a number of different backends, including Vulcan and WebGL (and Directx, WebGPU, Metal).

We're VC backed, which is how we finance the project right now. Long term we plan to monetize additional (optional) services around Ambient, such as game servers.

Yeah that's the idea; as a user you build multiple independent modules, which each are compiled in isolation, and which each produce a WASM module. The runtime then loads that module. All of this is very fast on the Rust toolchain with incremental builds, though of course it depends on the user breaking their code up into reasonably sized modules. The modules can independently be hot-reloaded (we had this before but it went away in a refactor, but we're planning to re-add again).

Ambient CPTO here; Yeah that's pretty much how it works; changes on the server state and replicated to clients, which keeps "mirrors" of that state and can augment it in different ways. And yes you can specify exactly which entities and/or components get replicated to the clients. We're working on adding more details on the networking stack: https://github.com/AmbientRun/Ambient/issues/150