AGI Watchful Guardians

We're open for new collaborations.
News to be updated weekly.

  • Home
  • About
  • Alignment Newsletter in Chinese
  • Nick Bostrom’s latest work in Chinese
  • Research
  • What would a Provably Safe AGI Framework look like?

    What would a Provably Safe AGI Framework look like?

    Xiaohu Zhu

    —

    Apr 8, 2024

    ×

    AGI, AI Safety, Beneficial, CSAGI
  • AN #102 通过 GPT-3 的元学习和人工智能对齐的完全提议列表

    Xiaohu Zhu

    —

    Jul 8, 2020

    ×

    AGI, AI Safety, Alignment
  • AN #103 ARCHES:存在性安全的议程和组合自然语言的深度强化学习

    Xiaohu Zhu

    —

    Jul 8, 2020

    ×

    AGI, AI Safety, Alignment
  • 机器学习理论之狂欢 COLT2020

    Xiaohu Zhu

    —

    Jul 7, 2020

    ×

    Machine Learning Theory
  • AN #104 无法访问的信息带来的危险,以及我们可以从 COVID 了解到的有关人工智能对齐的经验

    Xiaohu Zhu

    —

    Jul 7, 2020

    ×

    AGI, AI Safety, Alignment
  • AN #100 智能体在执行时学习奖励函数 可能会出问题

    Xiaohu Zhu

    —

    Jul 6, 2020

    ×

    AGI, AI Safety, Alignment
  • AN #106 评价学到的奖励模型的泛化能力

    Xiaohu Zhu

    —

    Jul 6, 2020

    ×

    未分类
  • AN #105 人类的经济轨迹和优化可能的“真正”含义

    Xiaohu Zhu

    —

    Jul 6, 2020

    ×

    AGI, Alignment
  • Comments|Quantifying Differences in Reward Functions

    Xiaohu Zhu

    —

    Jul 5, 2020

    ×

    未分类
  • Logician|Boris Trakhtenbrot

    Xiaohu Zhu

    —

    May 31, 2020

    ×

    未分类
  • 第 98 期对齐周报 通过查看哪些梯度有用来了解神经网络训练

    Xiaohu Zhu

    —

    May 19, 2020

    ×

    AGI, AI Safety, Alignment
Previous Page
1 2 3 4 5 6 … 10
Next Page

©

AGI Watchful Guardians

  • Subscribe Subscribed
    • AGI Watchful Guardians
    • Already have a WordPress.com account? Log in now.
    • AGI Watchful Guardians
    • Subscribe Subscribed
    • Sign up
    • Log in
    • Report this content
    • View site in Reader
    • Manage subscriptions
    • Collapse this bar