Paul 警告超智能对齐失控风险
AI 导读
引用 Paul： "基于近期能力发展轨迹和对齐问题的持续困难，我现在认为存在一种重大风险：AI 能力的快速加速会在极短期内导致灾难性且不可逆的失控。" "如果我们在没有更稳健对齐的情况下构建超智能，我预计我们将永久失去对它的控制。如果那发生，大多数人可能会死亡。"
正文
Quoting Paul:
"Based on the recent trajectory of capabilities and the continued difficulty of alignment, I now believe there is a meaningful risk that rapid acceleration in AI capabilities leads to catastrophic and irreversible loss of control in the very near term."
"If we build superintelligence without more robust alignment I expect we will permanently lose control of it. If that happens then most people could die."
https://x.com/i/article/2097730969369477120在 X 查看被引用的帖子