Amateur alignment proposal asks whether formalizing it would earn safety-community credit

jessi_cata · x · 2026-09-23

The author floats an idea for outer alignment, self-describing it as "not great" while asking the community for better approaches. They follow up asking whether writing the idea up at the formality level of the Quantilizers paper would earn them any credit from the AI safety community for helping with alignment.

The thread touches on the barriers and recognition mechanisms amateur researchers face when trying to contribute to AI safety discussions.

Related event: Hobbyist Proposes Time-Travel-Themed Outer Alignment Idea(2 posts)→

Original post →

More from Safety

Safety channel →