Joe Carlsmith's Substack
Subscribe
Sign in
Share this discussion
New report: "Scheming AIs: Will AIs fake alignment during training in order to get power?"
joecarlsmith.substack.com
Copy link
Facebook
Email
Note
Other
New report: "Scheming AIs: Will AIs fake…
Joe Carlsmith
Nov 15, 2023
1
Share this post
New report: "Scheming AIs: Will AIs fake alignment during training in order to get power?"
joecarlsmith.substack.com
Copy link
Facebook
Email
Note
Other
I examine the probability of a behavior sometimes called "deceptive alignment."
Read →
0 Comments
Share
Share
Copy link
Facebook
Email
Note
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
New report: "Scheming AIs: Will AIs fake alignment during training in order to get power?"
New report: "Scheming AIs: Will AIs fake…
New report: "Scheming AIs: Will AIs fake alignment during training in order to get power?"
I examine the probability of a behavior sometimes called "deceptive alignment."