AlignementMoral x 2

bookRéférences 1

The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process

This position paper states that AI Alignment in Multi-Agent Systems (MAS) should be considered a dyn...

2026-02-21 20:29:46

IntelligenceArtificielleAlignementMoralMilaComputer Science - Computers and Society

content_pasteContenus 1

Collective Constitutional AI: Aligning a Language Model with Public Input

Anthropic is an AI safety and research company that's working to build reliable, interpreta...

2025-05-01 20:52:26

Collective Constitutional AI: Aligning a Language Model with Public Input

IntelligenceArtificielleApprocheConstitutiveDeLaCommunicationAnthropicAlignementMoral

Mots-clés associés