•5 min read
Self-play training for augmented chess hit the home cluster's RAM ceiling
An AlphaZero-style pipeline for the augmented chess engine ran into 512Mi pod limits, and the fix taught me the difference between liveness and readiness probes.
#ai
2 posts tagged with ai. This index aggregates both frontmatter tags: entries and inline #ai mentions.
•1 min read
Building a Local LLM Gateway on a Mac Mini
A small OpenAI-compatible proxy in front of Ollama — Bearer auth, model routing, streaming — so no cluster pod has to hold a vendor API key.