Skip to main content
- AI Agents Coding agents and agent harnesses: tools, context and permissions.
- GPU Kernels CUDA and GPU kernels: attention, matmul, quantization and numerics.
- Life & Work Essays on work, careers and life.
- LLM Inference How LLMs run at inference time: tokens, attention, KV cache and decoding.
- Model Serving Serving engines and runtimes: requests, caches, scheduling and failure handling.
- Robotics Robot learning, embodied AI and robot foundation models.
- Video Generation Video diffusion models and the systems that run them.
- World Models Models that predict how the world evolves, for simulation and control.