The subagents ran thousands of numerical checks against known zeta zeros and refereed one another's work
子agents互相审核彼此的工作——scalable oversight在数学领域的实践。数学有客观正确性标准，所以AI peer review是可信的。真正的挑战是：在没有客观标准的领域（伦理、价值判断），这套机制是否还能成立？
2 Matching Annotations
- Last 7 days
-
www.anthropic.com www.anthropic.com
-
-
Claude volunteered to write its findings up as a paper, and recommended that a human number theorist validate its findings
Claude主动建议请人类数学家验证——AI主动寻求外部验证，知道自己可能出错。这种行为比结果本身更值得关注：一个足够智能的系统应该知道何时需要人类背书，而不是盲目自信。这是alignment的具体体现。
Tags
Annotators
URL
-