How judgments about beauty enter training and shape the recurring visual defaults of generated UI.

37 min read August 23, 2026

llm design ui

Human judgment shapes an agent's goals, assurance, authority, and accountability.

40 min read August 17, 2026

agent evaluation

How rewards become policy updates, and how data, credit assignment, and rollout systems come to define agentic RL.

124 min read August 13, 2026

llm rl

A mental model of GPU compute, memory, and communication, starting from the LLM operations researchers already know.

49 min read August 11, 2026

llm systems

How modern Transformers use positional mechanisms, compressed memory, conditional computation, and residual paths to reallocate model budgets.

130 min read July 22, 2026

llm architecture

A ground-up account of representation, transformation, interaction, scale, and low-rank structure inside LLMs.

58 min read June 16, 2026

llm math