home / www.anthropic.com / item 46707572
Summary ~lite AI Safety Advocates
Anthropic publishes Claude's new constitution, emphasizing AI safety, ethics, and transparency
Lite evaluation by llama-4-scout-wai · editorial channel only · no per-section breakdown available
Longitudinal
· 3 evals
+1 0 −1 HN
Audit Trail
8 entries all eval pipeline all models llama-4-scout-wai llama-3.3-70b-wai
newest first
2026-03-01 00:02 model_divergence Cross-model spread 0.40 exceeds threshold (2 models) - - 2026-03-01 00:02 eval_success Lite evaluated: Strong positive (0.60) - - 2026-03-01 00:02
eval
Evaluated by llama-4-scout-wai : +0.60 (Strong positive) 0.00 reasoning Editorial stance on AI rights and safety, transparent and advocacy-oriented
2026-02-28 23:57 model_divergence Cross-model spread 0.40 exceeds threshold (2 models) - - 2026-02-28 23:57 eval_success Lite evaluated: Strong positive (0.60) - - 2026-02-28 23:57
eval
Evaluated by llama-4-scout-wai : +0.60 (Strong positive) reasoning Editorial stance on AI rights and safety, transparent and advocacy-oriented
2026-02-28 23:53 eval_success Lite evaluated: Mild positive (0.20) - - 2026-02-28 23:53
eval
Evaluated by llama-3.3-70b-wai : +0.20 (Mild positive) reasoning AI model constitution release