9th April 2024
llm.c (via) Andrej Karpathy implements LLM training—initially for GPT-2, other architectures to follow—in just over 1,000 lines of C on top of CUDA. Includes a tutorial about implementing LayerNorm by porting an implementation from Python.
Recent articles
- Two new Showboat tools: Chartroom and datasette-showboat - 17th February 2026
- Deep Blue - 15th February 2026
- The evolution of OpenAI's mission statement - 13th February 2026