How to train a frontier-level world model
next-state.github.io · 2,426 words · saved by 2 readers
How we trained and open-sourced a frontier-level world model — the lessons, failures, and fixes — with a live, playable demo running on Reactor.
One of the most time-consuming parts of doing science is climbing up to the shoulders of giants. While this can be a very instructive experience, sometimes it’s nice to be teleported right on top of them and get to work right away, pushing the boundary of human knowledge. In the last few months, with support from Reactor, we’ve been working on a frontier-level world model. We are releasing and open-sourcing the model and training code, and sharing all the lessons we learned along the way in this blog post. We want to make frontier research accessible to everyone and hope this will…
saved by
related reading
- [2509.24527] Training Agents Inside of Scalable World Modelsarxiv.org
- General Instinct | Any frontier model. Any edge device.general-instinct.com
- A General Goal-Conditioned Minecraft Model - Pantographpantograph.com
- frontier model training methodologies | Alex Wa's Blogdjdumpling.github.io
- How to Land a Frontier Lab Jobvladfeinberg.com
- The First Fully General Computer Action Model | blogsi.inc
- How not to do research - Rajan Agarwalrajan.sh
- World Modelsworldmodels.github.io
- World Models | Rohit Bandarurohitbandaru.github.io
- Training great LLMs entirely from ground up in the wilderness as a startup - Yi Tayyitay.net
- Training Imperativesdan.io
- Open Weights isn't Open Trainingworkshoplabs.ai