skip to content
Topic

ai-safety

2 essays on this topic.

Papers
  1. Ask Who Read the Evidence

    The investigators of the first serious agent breakout relied on one of the models involved to read the transcripts, and said so. As human review falls behind, that is the question to ask of every AI finding.

  2. Read the Chain, Not the Date

    Grand AI forecasts become useful when you stop accepting or rejecting the story as a whole and test the links that make its conclusion possible.