Anthropic x 8
constructionOutils 1
Claude is AI for all of us. Whether you're brainstorming alone or building with a team of t...
2025-08-26 12:11:42
newspaperActualités 2
bookRéférences 1
Collective Constitutional AI: Aligning a Language Model with Public Input
There is growing consensus that language model (LM) developers should not be the sole deciders of LM...
2026-02-21 20:29:46
IntelligenceArtificielleApprocheConstitutiveDeLaCommunicationAnthropicParticipationPubliqueComputer Science - Computation and LanguageComputer Science - Human-Computer Interaction
content_pasteContenus 4
Claude 4.5 Opus' Soul Document — LessWrong
Update 2025-12-02: Amanda Askell has kindly confirmed that the document was used in supervised learn...
2025-11-28 00:00:00
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
IntelligenceArtificielleApprocheConstitutiveDeLaCommunicationAnthropicAlignementMoral
Tracing the thoughts of a large language model
Anthropic's latest interpretability research: a new microscope to understand Claude...
