Snipd home pageGet the app
public
The Inside View chevron_right

Tony Wang on Beating Superhuman Go AIs with Advesarial Policies

Aug 4, 2023
03:35
forum Ask episode
view_agenda Chapters
auto_awesome Transcript
info_circle Episode notes
1
Introduction
00:00 • 3min
chevron_right
2
Explode AlphaGo in 2016
03:14 • 2min
chevron_right
3
How to Train Your Own AI Using Alpha Ghost Operator
05:04 • 2min
chevron_right
4
How to Find an Exploit for Cotego's Newest Version
06:34 • 3min
chevron_right
5
The Robustness of AI Systems
09:13 • 4min
chevron_right
6
Exploits for Language Models
13:24 • 3min
chevron_right
7
The Intent Alignment Problem
15:58 • 2min
chevron_right
8
The Future of Life in the Two
18:10 • 2min
chevron_right
9
How to Deal With a Stressed Out User
20:31 • 2min
chevron_right
10
How to Solve the Problem of Alignment
22:33 • 2min
chevron_right

Tony is a PhD student at MIT, and author of "Advesarial Policies Beat Superhuman Go AIs", accepted as Oral at the International Conference on Machine Learning (ICML).

Paper: https://arxiv.org/abs/2211.00241


Youtube: https://youtu.be/Tip1Ztjd-so

HomeTop podcastsPopular guests