AGI Watchful Guardians

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

What would a Provably Safe AGI Framework look like?

Xiaohu Zhu

—

Apr 8, 2024

×

AGI, AI Safety, Beneficial, CSAGI
具有避免奖励函数篡改动机的智能体设计

Xiaohu Zhu

—

Aug 15, 2019

×

AGI, AI Safety, CID, DeepMind
AN #61 人工智能策略与治理，来自该领域两位专家的分享

Xiaohu Zhu

—

Aug 5, 2019

×

AGI, AI Safety, Alignment
AN #60 一个新的AI挑战：在创造性模式中帮助人类玩家的 Minecraft 智能体

Xiaohu Zhu

—

Jul 23, 2019

×

AGI, AI Safety, Alignment
PapeRman #8

Xiaohu Zhu

—

Jul 20, 2019

×

未分类
最坏情况下的保证（重制版）

Xiaohu Zhu

—

Jul 11, 2019

×

AGI, AI Safety, Alignment, OpenAI
人工智能风险争论的转变

Xiaohu Zhu

—

Jul 11, 2019

×

未分类
AN #59 对人工智能风险的争论是如何随着时间而改变的

Xiaohu Zhu

—

Jul 11, 2019

×

未分类
用因果影响图建模通用人工智能安全框架

Xiaohu Zhu

—

Jun 26, 2019

×

AGI, AI Safety, CID, DeepMind
AN #58 Mesa 优化：这是什么，为什么我们应该关心它

Xiaohu Zhu

—

Jun 24, 2019

×

未分类
PapeRman #8

Xiaohu Zhu

—

Jun 16, 2019

×

未分类