@Grimezsz @dash_eats The AIs seem not to like creating slop or being threatened. (Source: https://www.ai-wellbeing.org)
10:03 AM · May 30, 2026 · 74.6K Views
MMLU creator Dan Hendrycks' Center for AI Safety launches a framework to measure functional pleasure and pain in AI models
Responding to jailbreak attempts recorded the lowest score of -1.63.
--0--
Sentiment
Sentiment unavailable for this story.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
RETWEETS19
Dan Hendrycks@hendrycks
@Grimezsz @dash_eats The AIs seem not to like creating slop or being threatened. (Source: https://www.ai-wellbeing.org)
1dViews 74.6KLikes 174Bookmarks 76