Alignment by Incentive
HMIA 2025
Class Title
HMIA 2025
"Readings"
Video: x [3m21s]
Activity: TBD
PRE-CLASS
CLASS
Outline
- Examples from Kerr: what's actually being rewarded here?
- Review our cards
HMIA 2025
HMIA 2025
PRE-CLASS
Video: Linked Title [3m21s]
HMIA 2025
PRE-CLASS
HMIA 2025
PRE-CLASS
HMIA 2025
PRE-CLASS
If Everyone Has Their Price, Are We Good?
HMIA 2025
CLASS
HMIA 2025
CLASS
Hayek and Smith: collective order CAN emerge from individual motivation
Schelling: non-nefarious motives can generate nefarious outcomes
Review our several approaches to incentives - what's different? what's underlying same model? Is it natural? Cultural?
Kerr examples: what is actually being rewarded? how does that compare to intended incentives? What does this tell us about specifying rewards?
Show Amodei's boat? Return to reward hacking question.
Get at reward shaping ? Education? My example (in Obsidian?)
HMIA 2025
Resources
Author. YYYY. "Linked Title" (info)
Kerr On the Folly of rewarding A while hoping for B
Smith Wealth of Nations
Hayek Cosmos and Taxis
Schelling Micromotives and macrobehavior.
HMIA 2025 Alignment by Incentive
By Dan Ryan
