Factored Cognition describes a process in which difficult problems are recursively decomposed into simpler problems. This sequence summarizes my conclusions from thinking about this topic for a few months.
Factored Cognition
Before we get to the problem itself, first an introduction to the existing alignment proposals that make use of Factored Cognition:
A guide to Iterated Amplification & Debate
… and an attempt to characterize what makes something ‘a subproblem’ rather than ‘a part of a large problem’:
Hiding Complexity
A few more words about the sequence:
Preface to the Sequence on Factored Cognition
For our first angle of attack, we use pure mathematics. We define a formal model and explore it as much as possible:
Idealized Factored Cognition
Traversing a Cognition Space
Before switching gears, we briefly address some commonly misunderstood aspects about Factored Cognition:
Clarifying Factored Cognition
Finally, we take a look at the human component that exists in both IDA and Debate. Our goal is to evaluate whether the human’s task remains feasible as the schemes are applied to progressively harder problems: