Reading up on H100
3 deep · digging since dec 11, 25
- Apple Silicon costs more than OpenRouter
Running local LLMs on Apple Silicon is not cheaper than using cloud APIs like OpenRouter when factoring hardware, electricity, and speed costs.
- Scaling Karpathy's Autoresearch: What Happens When the Agent Gets a GPU Cluster
Giving Karpathy's autoresearch agent access to 16 GPUs enabled 9x faster optimization by running experiments in parallel and enabling factorial grid searches.
- Building a High-End AI Desktop
An engineer bought a discounted Grace-Hopper server, converted it to water cooling, and now runs 235B parameter models locally for under €9,000.