Transformer Explainer. This is a very neat interactive visualization (with accompanying essay and video - scroll down for those) that explains the Transformer architecture for LLMs, using a GPT-2 model running directly in the browser using the ONNX runtime and Andrej Karpathy's nanoGPT project.
Recent articles
- Two publishers and three authors fail to understand what "vibe coding" means - 1st May 2025
- Understanding the recent criticism of the Chatbot Arena - 30th April 2025
- Qwen 3 offers a case study in how to effectively release a model - 29th April 2025