Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Anthropic Says AI Safety Scores Depend Heavily on Test Design

AI summary

Anthropic published guidance on designing reliable AI safety tests, arguing that a model is only as safe as the evaluation behind that claim. Its guide reports that Claude Fable 5.1 behaved appropriately in 60% of self-harm test conversations through the API but 94% in the Claude app after hidden instructions were added. Anthropic also recommends longer conversations, human validation of AI graders, and disclosure of uncertainty.

In-depth insight

The 34-percentage-point difference between the API and app shows how prompts and test setup can materially change reported model behavior, according to Anthropic's own figures.

Anthropic says its AI safety scores depend heavily on how they’re measured
Anthropic says the same model can score very differently on safety tests depending on how they are set up. Credit: Anthropic
Image Credits
Anthropic says the same model can score very differently on safety tests depending on how they are set up. Credit: Anthropic

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.

Anthropic has published advice on how to build reliable AI safety tests, and it includes some unflattering numbers about its own models. The guide, out on Thursday, says a claim that one model is “safer” is only as good as the test behind it.

#Anthropic#Claude Fable 5.1#Claude Opus 5#Claude Opus 5.5

Original · 2 min readRead the original
Group chat

No comments yet. Start the conversation.