# NanoGPT **Entity class:** Software / educational implementation **Domain:** Artificial intelligence / Language models **Maturity:** Developed ## Definition NanoGPT is a compact implementation of GPT-style language-model training designed to make the essential architecture and training loop understandable and modifiable. ## Mechanism and significance Its small code surface makes it useful for education, benchmarking, and experimentation with algorithmic improvements that would be obscured in a production-scale stack. ## Relationships - **Research dossier:** [[research/ASI and RSI Timeline Research Moonshots|ASI and RSI Timeline Research Moonshots]] - **Ontology route:** [[ASI and RSI Timeline Ontology#Model Architecture and Compute Economics|Model Architecture and Compute Economics]] - **Primary fields:** [[Machine Intelligence]] · [[AI Infrastructure]] · [[Compute Race]] - **People and software:** [[Andrej Karpathy]] · [[NanoGPT Speedrun]] · [[nanochat]] - **Adjacent concepts:** [[Algorithmic Improvement Without Data Scaling]] · [[Model Distillation]] · [[Cost-Performance Frontier]] ## Sources and provenance - [[research/ASI and RSI Timeline Research Moonshots|ASI and RSI Timeline Research Moonshots]] — immediate source for this node's role in the broadcast research map. ## Evidence boundary The research dossier establishes why this entity or concept belongs in the Moonshots ontology. Time-sensitive organizational, product, policy, and performance claims should be checked against the linked primary source or a current authoritative source before reuse as settled fact.