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
语言智能体的对齐

Xiaohu Zhu

—

Mar 27, 2022

×

AGI, AI Safety, Alignment, CSAGI, DeepMind
因果影响图的进展

Xiaohu Zhu

—

Jul 1, 2021

×

未分类
元式训练成的智能体实现了贝叶斯最优的智能体

Xiaohu Zhu

—

Jan 31, 2021

×

DeepMind
关于 F. Chollet 的“关于智能的测量”（2019）

Xiaohu Zhu

—

Nov 20, 2020

×

Intelligence
REALab：概念化篡改问题

Xiaohu Zhu

—

Nov 20, 2020

×

AGI, AI Safety, DeepMind
为什么降低训练神经网络的成本仍然是一个挑战

Xiaohu Zhu

—

Nov 18, 2020

×

未分类
Shakir Mohamed 对“好”的想象，改变的使命

Xiaohu Zhu

—

Nov 2, 2020

×

Beneficial
AN #108 为何需要仔细检查人工智能风险的争论

Xiaohu Zhu

—

Jul 16, 2020

×

AGI, AI Safety, Alignment, CSAGI
AN #107 目标导向的智能体的收敛工具性子目标

Xiaohu Zhu

—

Jul 10, 2020

×

AGI, AI Safety, Alignment, CSAGI
AN #101 为何我们需要严格度量和预测人工智能进展

Xiaohu Zhu

—

Jul 8, 2020

×

AGI, AI Safety, Alignment