Subscribe
Sign in
Share this post
Transformer
The way we evaluate AI model safety might be about to break
Copy link
Facebook
Email
Notes
More
The way we evaluate AI model safety might be…
Lynette Bye
Jan 22
Share this post
Transformer
The way we evaluate AI model safety might be about to break
Copy link
Facebook
Email
Notes
More
1
As systems become more capable, researchers think we need a new type of safety evaluation
Read →
Comments
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
Share this post
The way we evaluate AI model safety might be…
Share this post
As systems become more capable, researchers think we need a new type of safety evaluation