Sign inSign in
ConceptAI & ML

Plan divergence

A looping problem where an AI agent diverges from its task, makes mistakes, and continues randomly without knowing how to correct itself.
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Autonomous agents2Multi-turn interactions1Stochastic system1

Lecturers

2

Each in their own terms, from the easiest level.

  • Steven Feng

    Stanford University · Undergraduate

    A failure mode in multi-step AI agent trajectories where an error in an early step causes the agent's actual execution path to deviate completely from the ideal path.

Connections

3

The lectures that define it or assume it, and the concepts next to it.

Concept1

Lectures2

2 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.