Collections
An 11-part series on designing LLM decision systems whose information, tools, actions, memory, and evaluation can be validated and traced.
Explore the series Series · 22 partsA 22-part series on why noisy iterative updates can converge, from error recursions and step-size conditions to the Robbins–Monro conditions and Dvoretzky's theorem.
Explore the seriesLatest
Treating a generative model like a database reveals its missing schema: data must be decomposed into operational units. A Tetris example shows how decomposition granularity sets the model’s inductive bias, compositional freedom, and cost.
People do not simply apply different rules to identical inputs. Attention, experience, and representation shape the inputs themselves. Science makes maps shared and testable, but those maps remain bounded by instruments, scale, and domain.