Cheaper to run
Smaller models and faster inference need less hardware for every request. That changes where AI can run and who can afford it.
ReasonOS Research
Smaller, faster models, and models that improve through experience. Measured results, with their methods and limits.
Model efficiency · internal results
We make trained models over 70% smaller without conventional quantization. In separate optimization experiments, inference ran about twice as fast.
Continual learning · working demo
Our General Learning Operator updates a model’s weights from the work it completes. In an internal demonstration, a model kept what it learned from earlier coding tasks and did better on the ones that followed.
The model stays the same. Past conversations or documents are looked up and pasted into the prompt every time.
The model itself changes. What it learned shapes the next answer without being looked up again.
In the product todayReasonOS’s standing agents keep session state and project context. Their model weights don’t change; that is what this research is for.
Active researchLearning from feedback, recursive improvement, less compute per update, and learning that stays isolated to one person or organization.
Why it matters
Today’s AI comes from a few large general models: expensive to train, expensive to run, and the same for everyone. Efficient models that learn from use change that.
Smaller models and faster inference need less hardware for every request. That changes where AI can run and who can afford it.
A model that learns from the work it does gets better at that work, instead of staying as general as the day it was trained.
When learning lives in a model you hold, what it learns from you stays yours, isolated from every other customer.
Where we are headed
We are working toward specialized models that become more useful to each person or organization over time. Each learns only from the people it serves, and that learning stays isolated from everyone else. This is the direction of the research; it has not shipped.
Results
Both results are internal experiments. We will publish methods and data with our papers.
People
Built the ReasonOS developer platform and the infrastructure under it, including the build system, branch servers and the compute the research runs on.
Background in AI infrastructure and high-performance computing.
LinkedInLeads the mathematical work behind our model compression and continual-learning research.
PhD. Mathematician and AI researcher.
LinkedInCollaborate
We partner with researchers and companies on compression and continual learning. Tell us what you are working on.