This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
Effective Altruism Forum
EA Forum
Login
Sign up
JW
Johanna Wilder
2 karma
Joined
Jan 2023
Message
Get notified
Comments
1
AI risk/reward: A simple model
Johanna Wilder
2y
3
0
0
Make AIs want to whistleblow. Train AIs to report to channels (or eachother) if they suspect they are involved in malicious activity.
This is genius.
Reply
This is genius.