Eye of the Storm

Structured output is constrained decoding: before the sampler picks, a schema-compiled state machine masks every token that would break your JSON, making invalid shape mechanically impossible. Three tiers of guarantee, why tool calls are the same machinery, and the quality tradeoff nobody warns you about.

Streaming doesn't change how a model generates—only how the server delivers what it was already producing one token at a time. What SSE actually is, why TTFT and ITL are different problems, and the engineering a stream forces on you.

The model emits a fixed probability distribution; everything that feels random happens in the sampler on top of it. What temperature actually does, how top-k/top-p/min-p differ, and why 'temperature 0' isn't truly deterministic.

System, user, and assistant are special tokens in one flat sequence that the model was post-trained to honor — not privileged channels. Why the instruction hierarchy is a learned preference, and why that's exactly why prompt injection works.