Redwood Research blog

Redwood Research blog

Share this post

Redwood Research blog
Redwood Research blog
Misalignment and Strategic Underperformance: An Analysis of Sandbagging and Exploration Hacking

Misalignment and Strategic Underperformance…

May 8
11

Share this post

Redwood Research blog
Redwood Research blog
Misalignment and Strategic Underperformance: An Analysis of Sandbagging and Exploration Hacking

A new analysis of the risk of AIs intentionally performing poorly.

Read →
Comments
User's avatar
© 2025 Buck Shlegeris
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share