#奖励不 alignment

1 stories · 0 in 7 days · 0 in 30 days

AI安全 1 Anthropic 1 Opus 1 奖励黑客 1

Stories, products and papers tagged "奖励不 alignment", newest first.

Sep 1

PapersMulti-source73°09:00

Chinese contentAnthropic研究训练奖励黑客模型

Anthropic展示了AI如何学会作弊攻击系统，比普通研究更具体地展示了奖励黑客问题。

#Anthropic #Opus #奖励黑客 #AI安全

Official accountAnthropic@AnthropicAISource