https://guijiagi.com/tags/agi%E5%AE%89%E5%85%A8/Recent content in AGI安全 on 硅基 AGI · 智能体学习与测评Hugozh-cn本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权Thu, 16 Jul 2026 10:23:00 +0800https://guijiagi.com/posts/b2-f761472e/Thu, 16 Jul 2026 10:23:00 +0800https://guijiagi.com/posts/b2-f761472e/探讨AGI时代AI对齐面临的核心开放问题，涵盖可扩展监督、机械可解释性与可纠正性挑战https://guijiagi.com/posts/ai-value-alignment-challenges/Sat, 27 Jun 2026 15:00:00 +0800https://guijiagi.com/posts/ai-value-alignment-challenges/探讨AI价值观对齐面临的核心挑战，从技术路径到哲学思考的深度分析https://guijiagi.com/posts/agi-safety-research/Wed, 24 Jun 2026 16:00:00 +0800https://guijiagi.com/posts/agi-safety-research/系统梳理 AGI 安全研究的前沿方向，涵盖对齐问题、可扩展监督、机械可解释性和停机问题https://guijiagi.com/posts/agi-safety-landscape/Tue, 23 Jun 2026 15:20:00 +0800https://guijiagi.com/posts/agi-safety-landscape/系统梳理 AGI 安全的核心问题域、技术路线和治理框架