Dispatches from the AI Front Line

Position papers.

A four-part series about what happens when AI moves from controlled demonstrations into ordinary use. Each paper takes a borrowed word — memory, compaction, reasoning, agency — names the gap between what the word implies and what the feature delivers, and describes the infrastructure required before users can safely rely on it.

  1. Part 1

    AI Memory Is a Lie

    You are doing the work of believing it.

    Read →
  2. Part 2

    AI Compaction: A Euphemism for Loss

    What the friendly progress bar is actually doing to your conversation.

    Coming
  3. Part 3

    AI Reasoning: Inference Through a Keyhole

    Why generated chains of thought are not what the word "reasoning" implies.

    Coming
  4. Part 4

    AI Agency: Rolling Dice on the Operating Table

    Why scripted tool-use loops are not what the word "agent" implies.

    Coming