Redwood Research blog
Subscribe
Sign in
Share this post
Redwood Research blog
Misalignment and Strategic Underperformance: An Analysis of Sandbagging and Exploration Hacking
Copy link
Facebook
Email
Notes
More
Misalignment and Strategic Underperformance…
May 8
11
Share this post
Redwood Research blog
Misalignment and Strategic Underperformance: An Analysis of Sandbagging and Exploration Hacking
Copy link
Facebook
Email
Notes
More
A new analysis of the risk of AIs intentionally performing poorly.
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
Misalignment and Strategic Underperformance…
Share this post
A new analysis of the risk of AIs intentionally performing poorly.