The models are smarter than you, you just have more context

I needed an agent to do workforce scheduling. One-shot prompting failed, so I built a hierarchical system instead. This post walks through the architecture and the tradeoffs.

The economics of building software are changing

An analysis of LLMs' ability to construct constraint-optimized employee schedules

A simple framework for iterating quickly to identify what works when building with LLMs

A handful of recent projects with LLMs

Why many executives spend time on 'minor' details, and why it is rational to do so

Improving LLM capabilities through increased runtime compute and better specialization.

Most market-driven activity has different properties than chess that will result in less human-centricity

Fixed-cost economics mean it is unlikely that dramatically longer context windows will replace fine-tuning

Speed and efficiency are often at odds in project management; it is worth considering which you are optimizing for

Explaining the gap between perception and reality of what consulting firms are selling

Review of Brian Arthur's fascinating theory of the true nature of technology and the resulting implications