ARC and @aicrowdHQ are launching a ≥$100k contest for white-box estimation algorithms: given the weights of an MLP, the goal is to estimate the expected output of the network on Gaussian inputs. (Thread)
9:21 AM · Jun 4, 2026 · 5.3K Views
Alignment Research Center's Jacob Hilton launches a $100,000 challenge to estimate MLP outputs directly from network weights
A warm-up round for the competition is currently live.
--0--
Sentiment
Sentiment building, check back later.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS4.5KBOOKMARKS16LIKES38RETWEETS5REPLIES4
Ryan Greenblatt@RyanPGreenblatt
It would be nice if AI companies and others (e.g. startups) tried to have their AIs hillclimb on this task.
ARC is approximately our only current bet on scalable/worst-case solutions to alignment and they could be boosted by relatively checkable work!
Jacob Hilton@JacobHHilton
ARC and @aicrowdHQ are launching a ≥$100k contest for white-box estimation algorithms: given the weights of an MLP, the goal is to estimate the expected output of the network on Gaussian inputs. (Thread)
3hViews 4.5KLikes 38Bookmarks 16