Matto
Search
Search
Dark mode
Light mode
Reader mode
Recent Notes
Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures
Jun 08, 2026
Making Deep Learning Go Brrrr From First Principles
May 19, 2026
Defeating Nondeterminism in LLM Inference
Apr 29, 2026
Home
❯
Reviews
❯
Using AI to write better code more slowly
Using AI to write better code more slowly
Jun 04, 2024
1 min read
Blog post.
Graph View