4 posts tagged with ai. This index aggregates both frontmatter tags: entries and inline #ai mentions.
The Black and White bot looked strong — until you noticed it always played its 9 against a black opener. A human could bait that. Here's how we measured the exploit, found the root cause, and taught the model to stop being predictable — without resorting to play-time randomness.
The chess-ai stack had 94 files and 104 tests but never produced a single trained model. This time we picked the smallest game, closed the loop in a day, and let an automation session find six design flaws on its own metrics trail.
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.
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.