MIT Technology Review · AI· Amit Katwala·· 4 h ago
How “reverse game theory” could keep AI agents in check
How “reverse game theory” could keep AI agents in check
AI summary
A new approach known as “reverse game theory” aims to create incentives for powerful AI models that make following the rules the most rational choice.
Selection record
Threshold 76Media and individualsFirst 38Second 34
Not admittedSum of both 72 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：讨论AI对齐与机制设计方法
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: MIT Technology Review · AI · technologyreview.com