AI ALIGNMENT FORUMTags
AF

Principal-Agent Problems

•

Applied to 7. Evolution and Ethics by Roger Dearnaley 10mo ago

•

Applied to How could AIs 'see' each other's source code? by Gunnar Zarncke 1y ago

•

Applied to The Linguistic Blind Spot of Value-Aligned Agency, Natural and Artificial by Roman Leventov 2y ago

•

Applied to Air Conditioner Repair by Tobias D. 2y ago

•

Applied to Conservative Agency with Multiple Stakeholders by Alex Turner 3y ago

•

Applied to Buying a house and making friends in unexpected places by Adam Bull 4y ago

Jim Babcock v1.1.0Nov 9th 2020 GMT (+159)

A Principal-Agent Problem is when a decision is delegated to an agent, and the agent is incentivized to make choices other than those the principal would want.

•

Applied to Superintelligence 13: Capability control methods by Jérémy Perret 4y ago

•

Applied to What can the principal-agent literature tell us about AI risk? by Jérémy Perret 4y ago

•

Applied to Principals, agents, negotiation, and precommitments by Jérémy Perret 4y ago

•

Applied to The Alignment-Competence Trade-Off, Part 1: Coalition Size and Signaling Costs by Raymond Arnold 4y ago

•

Created by Raymond Arnold at 4y