PulseAugur / Brief
EN
LIVE 11:35:58

Brief

last 24h
[1/1] 223 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges

    Researchers have developed a new training strategy for AI safety judges, aiming to improve their consistency and reliability. The strategy involves using dynamic rubrics generated from prompt-response-label triples to expose judges to varied evaluation criteria. A curriculum approach progressively introduces these dynamic rubrics after initial training on fixed rubrics, leading to a 12B model that achieves high accuracy and stability across different rubric formulations. AI

    IMPACT Enhances the reliability of AI safety evaluations, potentially leading to more robust AI systems.