kodefreeze

Isn't this against their ToS? Useful for hobby stuff.

Last week, I posted about a hybrid approach I took to create low poly 3d assets for an RTS game I've been building. There was quite a bit of interest in a tutorial for it, so I created one and posted it on our blog.

Finally got around to posting a quick tutorial on the approach that's been working well for me. I don't believe LLMs or even diffusion models are ready to one-shot create game-ready assets. However, for those that are artistically challenged like me, a multi-step hybrid approach works really well as long as you are judging/iterating on the outputs at each step.

posted it here: https://news.ycombinator.com/item?id=49636173

Here's the tutorial - https://playwarpact.com/blog/lowpoly-hybrid/

Here's the tutorial - https://playwarpact.com/blog/lowpoly-hybrid/

thank you! working on it, will post soon.

These are not game ready unfortunately. It will be clear that they are AI generated due to not so good mesh quality.

meshy.ai , tripo are good ones to use. They give you free credits as well. If you already have the low poly model its easy to apply textures for it.

> then fit it back to the world with PCA + BB's

Can you expand on this?

I've tried several AI 3d generators that claim low-poly output, and they're all far off. None of them decide what belongs in the mesh vs. what should be baked in with the texture, so the poly budget lands in the wrong places.

Did you animate a 3d model of the car? or its a fully procedurally built animation?

Sorry, the game is still in dev and recently opened up for early access. I am working on a marketing page for the game that would link to the gameplay.

Will write it up!

I have experimented with this type of modeling for a RTS game I'm building: https://playwarpact.com

Few things:

1. Opus 5 is just as good for this tbh and cheaper.

2. They don't generate optimized 3d models. They have high poly count for simple geometries.

3. A better approach I've utilized for game ready assets is to use the model to create low poly silhouettes of the 3d model and then bake textures that include a lot more details like windows, doors etc with tools like Meshy. Can post a tutorial if there's interest.

The models need some more RL to be able to do this autonomously.

It's time for gpt 5.6 to come out too now.

Thank you, it's very early, we wanted to understand how interested people would be so building in the open.

We are building a command & conquer style RTS. If you're interested in taking a look at our very early demo of the game play, please check out: https://warpact-rts-9221.web.app/

And join our discord to follow along!

great question! we have logic to look for things like when certain network requests are completed, dom loaded, etc as well as a timeout so we are not waiting for ever. The LLM based on the screenshot can also decide to wait longer if the page hasn't fully loaded despite the checks we do.

They have browser automation, and a bunch of other agent tools to manage tasks, do things like PowerPoint slides, etc. I find chatgpt agent mode better for most tasks though.

Interesting that Meta is acquiring a Chinese company.

I was a fan of their initial product but I find it slower than chatpgpt agent mode. And the pricing is not great for individual users.

They raised at a ~6B round recently. I could have invested but missed the deadline :(

Do you have support for whatsapp group management?

I just did this test with our web QA agent - kodefreeze.com, it was able to test creating an account until it reached the screen that requires email confirmation.

Support for being able to receive email/custom actions is on our roadmap, but would love to see if getting this far would be valuable to you. The test was with the email=test@kodefreeze.com.

Thanks for letting us know, we'll fix it.

Please let us know if you have any feedback!

Sorry that you are running into this error, are you seeing this on the marketing website? or somewhere in the app?

How do you build trust in a system like that? The flowchart style have the advantage that you can decide when you want a human to review/approve as well as ensuring actions that need to happen at certain conditions do happen.

They've being doing some research on this: https://machinelearning.apple.com/research/ferretui-mobile

This is really interesting. We've been working on a smaller set of this problem space. We've also found in some cases you need to somehow pass to the model the sequence of events that happen (like a video of a transition).

For instance, we were running a test case on a e commerce website and they have a random popup that used to come up after initial Dom was rendered but before action could be taken. This would confuse the LLM for the next action it needed to take because it didn't know the pop-up came up.