# nanochat **Entity class:** Software project **Domain:** Artificial intelligence / Language models **Maturity:** Developed ## Definition nanochat is Andrej Karpathy's minimal, hackable system for training and interacting with a GPT-style language model across tokenization, pretraining, fine-tuning, evaluation, and inference. ## Mechanism and significance Its time-to-GPT-2 leaderboard turns an end-to-end training pipeline into a measurable arena for algorithmic and systems improvement. ## 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]] - **Adjacent concepts:** [[Recursive Architectural Self-Improvement]] · [[Model Self-Redesign]] · [[NanoGPT Speedrun]] · [[Algorithmic Improvement Without Data Scaling]] - **People and software:** [[Andrej Karpathy]] · [[NanoGPT]] ## 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. - [nanochat repository](https://github.com/karpathy/nanochat) — primary organizational or project source. ## 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.