UC教授：AI安全应承认不确定性
精选理由
UC教授Russell分享AI安全新思路，承认不确定性比盲目追求准确更关键。
UC Berkeley计算机科学教授Stuart Russell提出，AI安全的关键在于承认对人类目标的不确定性。他认为存在第三种选择，即对人类目标保持不确定。这种不确定性对AI安全至关重要。相关观点在AI Deep Dive节目中详细阐述。
原文 · The Information
What if safer AI starts with admitting it doesn’t know what you want?
“There's a third option, which is uncertain about what the human objective is. And that uncertainty turns out to be crucial.” — UC Berkeley computer science professor Stuart Russell
🚀 Watch the full episode of AI Deep Dive: https://t.co/Vt8X9fSwKD