Hacker Newsnew | past | comments | ask | show | jobs | submit | MasterScrat's commentslogin

Damn the pelican guy can’t get no sleep

> xAI is renting out their DC space. I think I read that Google is, too.

You’re probably thinking of Meta. Google renting GPUs is a less recent phenomenon, to say the least.



From HF:

> The practical lesson for defenders: have a capable model you can run on your own infrastructure vetted and ready before an incident, both to avoid guardrail lockout and to keep attacker data and credentials from leaving your environment.

This sounds like a reasonable measure. Any recommendations regarding the most suitable models for this? GLM? Kimi?


How is what you describe "YC-ish"?


Playing backward is actually a great idea for testing generalization


Hey all, happy to see this here! This was a colab between General Intuition (that I’m part of), Kyutai and Epic Games.

You can read plenty of details in the blog post and tech report but the TLDR is that we trained a multiplayer world model on 10k hours of Rocket League data. We optimized it to be playable at 20fps on a single GPU.

So what you see in the demo is fully generated: there’s no graphics or physics engine. Instead it’s a 5b neural network that takes actions in and gives pixels out.


Could a network be trained to transform physics state directly into the latent state and back?

Having a direct transformation would enable some interesting experiments.

How is the latent state different when everything else stays the same, but you change one physics value, like player one velocity? Is there a cyclical pattern of activation that correlates strongly with the seconds digit of the clock? Can you decode the latent state, give players full boost, and then re-encode it for infinite boost, without losing continuity?

Edit: There sure are a lot of papers on interpretability.


Would be a great idea to see how much we could manipulate the latent space and whether it has some internal structure w.r.t the physical state. I guess the only unknown is how the world model would show robustness to latent states that are transformed through this network


Tim Sweeney’s interviews on the uses of GenAI for game development have been some of the best takes I’ve heard. He’s mentioned how GenAI is great at filling in the gaps or treating assets, but no world simulation means no deep persistence or authoring for a whole new unique game world.

What is the conversation like within Epic now? Is this still the view? What is the future for simulations like this?


Very cool, and publishing a slice of the dataset and all of the training code is fantastic, but if reproducing the model and the video representation codec is encouraged, why not open source the models or at least some variant of them?

I'd be interested in seeing if fine-tunes that include human gameplay data would be possible.


We're happy to release MIRA, a collaboration between General Intuition, Kyutai, and Epic Games.

Mira was trained on 10k hours of Rocket League data. The model has 5B parameters and runs 4-player games at 20 fps on a single B200 GPU.

We've released a playable online demo, an in-depth technical report as well as a 1k hour dataset of 4-players gameplay:

Technical report: https://mira-wm.com/paper Repo: https://github.com/mira-wm/mira


How much compute did it take to train the model?


The checkpoint also weights half less than the game install! ;-)


This sounds like a strong statement with little backing. The author does infra at DeepSeek if his LinkedIn is to be trusted, and is the author of Foyer.


This is exactly what i would have needed 6 months ago


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: