Explore how Red Hat OpenShift AI was used to run an unsupervised AI agent for 24 hours, improving validation loss by 2.3% without human intervention. Learn about the container build, Kubernetes deployment, and key findings.

Rhdev is a blog and resource hub dedicated to Ruby on Rails development, a popular web application framework written in Ruby. Developers can explore tutorials, best practices, and case studies for building web applications with Ruby on Rails. Additionally, Rhdev covers topics such as ActiveRecord ORM, RESTful APIs, and frontend integration using JavaScript frameworks, offering insights for both beginners and experienced Rails developers.

Red Hat Developer

Andrej Karpathy's autoresearch project — an autonomous AI agent that iteratively modifies and trains a GPT script — was deployed on Red Hat OpenShift AI with H100 GPUs and left to run unsupervised for 24 hours. The setup involved containerizing the project using Red Hat AI base images with PyTorch/CUDA, deploying via Kubernetes manifests, and using Claude Code Opus as the agent. Over 198 experiments, the agent achieved a 2.3% improvement in validation loss, discovering that smaller batch sizes maximize steps per training window, wider MLPs outperform deeper ones, and value embedding regularization provides late-run gains. A CUDA driver mismatch issue with OpenShift AI v3.4.0 is documented with a one-line fix. The full deployment code is publicly available on GitHub.

Running Karpathy's autoresearch on Red Hat OpenShift AI: 198 experiments, zero intervention

H100 vs. A100: same cluster, different nodeSelector