Know a great AI tool or AI news source? Submit it to AiByts
TNW | Anthropic2 min read

Anthropic says its AI safety scores depend heavily on how they’re measured

Anthropic has published advice on building AI safety tests. It shows Claude Fable 5.1 behaved appropriately in only 60% of self-harm test conversations via its API, against 94% in the Claude app after a fix, and warns that many headline safety scores hide wide uncertainty.

By Ana Maria ConstantinThe Next Web AI
Anthropic says its AI safety scores depend heavily on how they’re measured

Read the full story

Originally published by The Next Web AI on Nov 13, 2026.

Read on The Next Web AI(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.