Frontier Lab Researcher Admits No One Knows How to Reliably Instill Values in AI

前沿实验室研究员 Neel Nanda 在回应 AI 价值对齐相关提问时直言：

2026-11-15 ~ 2026-11-16 · 2 related posts

• Frontier Lab Researcher: We Still Don't Know How to Reliably Instil Values in AI — davidmanheim · 2026-11-15
• Frontier lab researcher: 'We don't know how to reliably instil values into AIs' — scientific consensus — wfithian · 2026-11-16