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
第 99 期对齐周报算法效率的增倍时间

Xiaohu Zhu

—

May 16, 2020

×

AGI, AI Safety, Alignment
近似KL散度

Xiaohu Zhu

—

Apr 26, 2020

×

KL divergence, KL divergence
规格欺骗：人工智能创造力的另一面

Xiaohu Zhu

—

Apr 23, 2020

×

AGI, AI Safety, CSAGI, CSAGI, DeepMind
新研究工作简介：塑造行为的动机

Xiaohu Zhu

—

Feb 7, 2020

×

AGI, AI Safety, DeepMind
AN #75 用学到的游戏模型解决 Atari 和围棋问题以及一位 MIRI 成员的想法

Xiaohu Zhu

—

Dec 2, 2019

×

AGI, AI Safety, Alignment
AN #74 将向善的人工智能分解为能力、对齐和应对影响

Xiaohu Zhu

—

Dec 2, 2019

×

AGI, AI Safety, Alignment
Gated linear networks

Xiaohu Zhu

—

Nov 27, 2019

×

未分类
AN #73 通过了解智能体如何崩溃来检测灾难性故障

Xiaohu Zhu

—

Nov 18, 2019

×

AGI, AI Safety, Alignment
AN #72 对齐、健壮性、方法论和系统构建是人工智能安全的研究重点

Xiaohu Zhu

—

Nov 10, 2019

×

AGI, AI Safety, Alignment
A Comparative Analysis of Expected and Distributional Reinforcement Learning

Xiaohu Zhu

—

Nov 7, 2019

×

未分类