AppleSilicon

• June 30, 2026 Ornith 35B writes its own training scaffold: I put the self-improving coding model to the test on a Mac Mini M4 Pro
• February 14, 2026 LLM Inference Internals: KV Cache, Flash Attention, and Optimizing for Apple Silicon
• February 14, 2026 I Ran an 80B Coding Model Locally with Claude Code. It Took 1 Hour Instead of 9 Minutes. Here's What Was Wrong.