( Writing )
AI agents, blockchain, production software, and the hard problems in between. No hype — just what I've actually built, broken, and learned.
Patch tokenization, BSQ quantization, a causal transformer, and arithmetic coding — built from the ground up. Here's what broke, what worked, and where this research is headed.
The paper described the model. Here's what actually happened when we deployed it on 24 H100 GPUs at a major cancer center—the infrastructure decisions, the failures, and the thing I wish I'd built first.
After building production AI systems—including one deployed on 24 H100s at a major cancer center—here's what actually kills agent projects before they ship.
After writing six books on blockchain and covering 49 Forbes articles on Web3, here's my honest assessment of what actually worked—and what was always theater.