Foundations
Chapter 2

The Underdetermination of Intelligence

Why successful behavior does not uniquely identify mechanism.

The same observed behavior can arise from very different learned mechanisms.

A model may achieve excellent test performance while relying on features, representations, or strategies that differ substantially from those we intended.

In this chapter

2.1 The Rashomon Effect

Many models can achieve essentially indistinguishable performance while implementing different solutions.

2.2 Underspecification

Training objectives often fail to uniquely determine the behavior we want outside the observed training distribution.

2.3 Adversarial Features

Models can rely on predictive features that are valid statistically but misaligned with the features humans expect.

2.4 Shortcut Learning

Learners frequently discover easier predictive strategies than the mechanism we intended them to learn.

2.5 Why Interpretability Follows

If behavior does not uniquely identify mechanism, we need another channel for discovering which solution was actually learned.

Interpretable Intelligence synthesizes work from across the field, including research from Guide Labs. Relevant authors and results are cited throughout.