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)→
More from Safety
- 1a3orn asks: can mech interp detect RL-induced 'split persona' behaviors in models? — 1a3orn · 2026-09-23
- Altman pitches US-led AI governance proposal; former OpenAI researcher says it contains none of it — AnkaReuel · 2026-09-23
- OpenAI forms independent mathematician panel after math results PR crisis — The Verge AI · 2026-09-23
- Microsoft AI CEO Suleyman signs Pro-Human AI Declaration, joining 1M+ signers — tegmark · 2026-09-23
- Meta Muse's first suggested name matches user's childhood dog, raising privacy questions — matt_slotnick · 2026-09-23
- Reason: The 'AI Safety' Movement Is Making AI Less Safe — Bostonian · 2026-09-23