--- title: Running Karpathy's autoresearch on Red Hat OpenShift AI:... description: 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... canonical: https://daily.dev/posts/running-karpathy-s-autoresearch-on-red-hat-openshift-ai-198-experiments-zero-intervention-uejxfvugu twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Running Karpathy's autoresearch on Red Hat OpenShift AI: 198 experiments, zero intervention | daily.dev og:description: 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... og:url: https://daily.dev/posts/running-karpathy-s-autoresearch-on-red-hat-openshift-ai-198-experiments-zero-intervention-uejxfvugu og:image: https://api.daily.dev/og/posts/UEjxfVuGu.png og:image:alt: Running Karpathy's autoresearch on Red Hat OpenShift AI: 198 experiments, zero intervention og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Running Karpathy's autoresearch on Red Hat OpenShift AI: 198 experiments, zero intervention **[Red Hat Developer](https://daily.dev/sources/rhdev)** · 4 min read · 1 upvotes · 0 comments ## Summary 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. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Andrej Karpathy’s 630-line Python script ran 50 experiments overnight without any human input](https://daily.dev/posts/andrej-karpathy-s-630-line-python-script-ran-50-experiments-overnight-without-any-human-input-pjqwmdwbv) · The New Stack · 45 upvotes · 0 comments - [Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster](https://daily.dev/posts/scaling-karpathy-s-autoresearch-what-happens-when-the-agent-gets-a-gpu-cluster-hccbqaaty) · SkyPilot · 26 upvotes · 2 comments - [Operationalize AI agents with OpenShift and Kubernetes primitives](https://daily.dev/posts/operationalize-ai-agents-with-openshift-and-kubernetes-primitives-txscvjqfi) · Red Hat Developer · 0 upvotes · 0 comments - [How to Build an AI Agent That Runs its Own LLM Experiments with autoresearch](https://daily.dev/posts/how-to-build-an-ai-agent-that-runs-its-own-llm-experiments-with-autoresearch-brly8l88g) · freeCodeCamp · 3 upvotes · 1 comments - [Orchestrate production RAG with OpenShift AI](https://daily.dev/posts/orchestrate-production-rag-with-openshift-ai-wyqmzql08) · Red Hat Developer · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#kubernetes](https://daily.dev/tags/kubernetes), [#gpu](https://daily.dev/tags/gpu), [#openshift](https://daily.dev/tags/openshift) [View this post on daily.dev](https://daily.dev/posts/running-karpathy-s-autoresearch-on-red-hat-openshift-ai-198-experiments-zero-intervention-uejxfvugu) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Running Karpathy's autoresearch on Red Hat OpenShift AI: 198 experiments, zero intervention","url":"https://daily.dev/posts/running-karpathy-s-autoresearch-on-red-hat-openshift-ai-198-experiments-zero-intervention-uejxfvugu","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/running-karpathy-s-autoresearch-on-red-hat-openshift-ai-198-experiments-zero-intervention-uejxfvugu"},"datePublished":"2026-04-07T03:42:30.474Z","dateModified":"2026-04-07T03:45:49.521Z","description":"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...","image":"https://developers.redhat.com/sites/default/files/styles/share/public/Red%20Hat%20Openshift%20AI_0.png?itok=EGHltugp","thumbnailUrl":"https://developers.redhat.com/sites/default/files/styles/share/public/Red%20Hat%20Openshift%20AI_0.png?itok=EGHltugp","isAccessibleForFree":true,"articleSection":"Red Hat Developer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Red Hat Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/2a8895f3216c4900bdc455585a4ad3e4","url":"https://daily.dev/sources/rhdev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/running-karpathy-s-autoresearch-on-red-hat-openshift-ai-198-experiments-zero-intervention-uejxfvugu","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,kubernetes,gpu,openshift","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Red Hat Developer","item":"https://daily.dev/sources/rhdev"},{"@type":"ListItem","position":3,"name":"Running Karpathy's autoresearch on Red Hat OpenShift AI: 198 experiments, zero intervention"}]} ```