A 'corrigible' agent is one that doesn't interfere with what we would intuitively see as attempts to 'correct' the agent, or 'correct' our mistakes in building it; and permits these 'corrections' despite the apparent instrumentally convergent reasoning saying otherwise.
Corrigibility is also used in a broader sense, something like a helpful agent. Paul Christiano has defined corrigibility as an agent that will help me:
- Figure out whether I built the right AI and correct any mistakes I made
- Remain informed about the AI’s behavior and avoid unpleasant surprises
- Make better decisions and clarify my preferences
- Acquire resources and remain in effective control of them
- Ensure that my AI systems continue to do all of these nice things
- …and so on