AI assistants will serve two masters and always want something in return
Evidence
These computational helpers of the near future, whether they appear in digital or robotic form—likely both—will almost without exception have conflicts of interest, the servants of two masters: their ostensible owner, and whatever organization created them. In this sense they will be like butlers who are paid on commission; they will never help us without at least implicitly wanting something in return. — Brian Christian, The Alignment Problem, 1191
Categorization
- XREF: Echoes the chapter’s beverage-ad doom case and the reading purpose about contradictory goals. — connects to: AI researchers aim to align general-purpose systems with hard-to-specify human intentions
- corroborated: 2 independent passages support this claim — Brian Christian, The Alignment Problem, 1191
Related
- Ensuring AI captures human intent is now a central computer science problem (similarity 0.81)
- Intent-alignment doesn’t specify whose intentions matter, leaving trade-off conflicts unresolved (similarity 0.80)
- AI alignment may require machines to pursue human objectives, not their own (similarity 0.79)