•8 min read
The learning rate was the real lever, not the network's size
We grew the YINSH game AI to a larger brain and discovered one hardcoded number had been silently defeating the idea before it got started.
Recently Published
View All•10 min read
270 generations of self-play: the clever tricks lost to raw capacity
270 generations of self-play on one GPU. A bigger network and a stricter referee won; the cheap clever tricks lost; the next lever is a hardware upgrade, not another idea.
•7 min read
The speedup that sped up nothing — when a flat line lies
After I made the YINSH AI's practice cheap, the referee became the slow part. I diagnosed the bottleneck, built a careful fix, proved it correct — and it made zero difference. This is the story of why a flat performance curve fooled me, and how to ship an honest negative result.
•7 min read
Winning sooner, not just winning — teaching the AI to value a quick kill
The YINSH AI thought a win one move away and a win a hundred moves away were exactly the same thing. Fixing that — teaching it to prefer winning sooner — made it both stronger and cheaper to run, and taught me the value network is a search multiplier, not just a scorekeeper.
•10 min read
Thinking smarter, not harder — a faster self-play loop that can't get less creative
The YINSH AI spends two-thirds of its training time practicing against itself. Three planned changes cut that time — the biggest replaces 800 brute-force look-aheads per move with about 50 clever ones — under one hard rule: it must not get less creative.
Browse by tag
#ai12#self-play9#yinsh9#alphazero7#gpu-training6#mcts6#kubernetes5#event-sourcing3#game-ai3#game-platform3#gitops3#architecture2#black-and-white2#claude2#debugging2#fluxcd2#graphknow2#infrastructure2#knative2#migration2#multiplayer2#neural-network2#observability2#security2#argocd1#authorization1#blog1#board-game1#board-game-client1#board-games1#build-optimization1#chess1#ci-cd1#cleanup1#concurrency1#config1#container-security1#deployment1#determinism1#docker1#e2e1#exploitability1#github-actions1#golang1#hidden-information1#homelab1#k3s1#knowledge-graph1#llm1#machine-learning1#memory-management1#meta1#mitmproxy1#monorepo1#nash-equilibrium1#neo4j1#oauth1#ollama1#onnx1#performance1#pivot1#probes1#profiling1#qdrant1#reinforcement-learning1#responsive1#retrospective1#sandbox1#self-hosted-runner1#share-links1#staging1#supply-chain1#training1#training-loop1#ux1#value-network1#websockets1#wireframes1#workflow1