Aurelius is a decentralized platform for generating high-quality AI alignment data by systematically probing language models to uncover safety failures and edge-case behaviors. It evaluates responses across multiple ethical and safety dimensions using open-source moderation tools, LLM-based judges, and custom alignment metrics. The aim is to create a transparent, verifiable foundation for alignment research and to build a long-term ecosystem where diverse perspectives help define, measure, and improve the safety of increasingly capable AI systems.
Anúncio
Anúncio
SN37
Ranque #1862Aurelius
0.89444
+0.03505782990
+4.08%
26 de set., 05:45 UTC
Sobre
Dado de