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
导向健壮和经验证的人工智能：规格测试，健壮训练和形式验证

Xiaohu Zhu

—

Mar 30, 2019

×

未分类
设计智能体动机机制来避免副作用

Xiaohu Zhu

—

Mar 13, 2019

×

AGI, AI Safety, DeepMind, Side effects
迷失于数学？

Xiaohu Zhu

—

Mar 9, 2019

×

未分类
PapeRman #6

Xiaohu Zhu

—

Mar 1, 2019

×

未分类
PapeRman #5

Xiaohu Zhu

—

Mar 1, 2019

×

未分类
PapeRman #4

Xiaohu Zhu

—

Mar 1, 2019

×

未分类
利用因果影响图来理解智能体动机

Xiaohu Zhu

—

Feb 28, 2019

×

AGI, AI Safety, CID, DeepMind
PapeRman #3

Xiaohu Zhu

—

Feb 2, 2019

×

未分类
An investigation of `an investigation of model-free planning`

Xiaohu Zhu

—

Jan 29, 2019

×

未分类
PapeRman #2

Xiaohu Zhu

—

Jan 29, 2019

×

未分类