Writing on technology, building, and engineering.
Memory, compute, and bandwidth are the only three budgets there are. Every technique for training and serving large language models — checkpointing, flash attention, GQA, quantization, ZeRO, tensor and pipeline parallelism, speculative decoding — spends one to buy back another. This is that ledger, derived rather than listed.
A guided walk through building, from scratch, a real reinforcement-learning environment for an LLM coding agent — the reset/step contract, a safe sandbox, a reward that resists hacking, and a real gpt-4o policy.
A practical, low-math introduction to options trading: calls, puts, payoff diagrams, the Greeks, and a paper-trading simulator.