News for hackers. Stuff that matters.

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.

Re:Fable 5.1 World Modeling on Wednesday September 09, 2026 @07:38PM (#49636181)
Re:Fable 5.1 World Modeling on Wednesday September 09, 2026 @07:37PM (#49636173)
Re:Fable 5.1 World Modeling on Wednesday September 09, 2026 @07:37PM (#49636164)
Re:Fable 5.1 World Modeling on Friday September 04, 2026 @02:54AM (#49561369)
thank you! working on it, will post soon.
Re:Fable 5.1 World Modeling on Friday September 04, 2026 @02:53AM (#49561359)
These are not game ready unfortunately. It will be clear that they are AI generated due to not so good mesh quality.
Re:Fable 5.1 World Modeling on Friday September 04, 2026 @02:50AM (#49561336)
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.
Re:Fable 5.1 World Modeling on Wednesday September 02, 2026 @07:14PM (#49543899)
Did you animate a 3d model of the car? or its a fully procedurally built animation?
Re:Fable 5.1 World Modeling on Wednesday September 02, 2026 @07:12PM (#49543879)
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.
Re:Fable 5.1 World Modeling on Wednesday September 02, 2026 @05:46PM (#49543013)
Will write it up!
Re:Fable 5.1 World Modeling on Wednesday September 02, 2026 @05:07PM (#49542571)
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.

Re:Fable 5 Is Back on Wednesday July 01, 2026 @03:55PM (#48752256)
It's time for gpt 5.6 to come out too now.
Re:OpenRA on Sunday June 28, 2026 @06:40PM (#48712496)
Thank you, it's very early, we wanted to understand how interested people would be so building in the open.
Re:OpenRA on Saturday June 27, 2026 @11:31PM (#48704062)
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!

Re:OpenRA on Saturday June 27, 2026 @10:48PM (#48703880)
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!

Show HN: UI testing using multimodal LLMs

https://kodefreeze.com

Hi HN,I built this tool to solve the "flakiness" problem in UI testing. Existing AI agents often struggle with precise interactions, while traditional frameworks (Selenium/Playwright) break whenever the DOM changes.The Approach: Instead of relying on hard-coded selectors or pure computer vision, I’m using a multi-agent system powered by multimodal LLMs. We pass both the screenshot (pixels) and...

( Read More... | no comments | on HN )
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.

Show HN: I built a product to test webapps like a user would

https://kodefreeze.com

Hi HN, sharing a product that I built since I didn't want to manual test our app.The approach used is a multi-agent system that uses an augmented vision based approach for interacting with the UI, rather than relying on the DOM. The goal is to mimic how your users would naturally use the UI, rather than following a predefined path.I built this because I got tired of doing manual QA for my last...

( Read More... | 2 comments | 2 points | on HN )
Re:ManusAI Joins Meta on Monday December 29, 2025 @10:45PM (#46429320)
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.
Re:ManusAI Joins Meta on Monday December 29, 2025 @10:43PM (#46429309)
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.

Re:Nvidia buying AI chip startup Groq for about $20B on Thursday December 25, 2025 @05:47AM (#46383611)
They raised at a ~6B round recently. I could have invested but missed the deadline :(
Re:Show HN: Kapso – WhatsApp for developers on Thursday December 25, 2025 @05:03AM (#46383423)
Do you have support for whatsapp group management?

Show HN: Kodefreeze – Automate UI testing with natural language tests

https://kodefreeze.com

Hi HN, sharing a SaaS product that I built to automate web UI testing based on natural language test descriptions. The approach we use is a multi-agent system that uses an augmented vision approach for interacting with the UI, rather than relying on the DOM. The goal is to mimic how your users would naturally use the UI, rather than following a predefined path.I built this because I got tired...

( Read More... | no comments | 3 points | on HN )
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 protected].

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.

Older »