aiqbench takeAI Policy

Anthropic's new Claude Fable 5 model intentionally restricts responses to basic biology queries, routing them to its older Opus 4.8 variant despite possessing the underlying knowledge to answer them. This design choice prioritizes conservative safety guardrails against bioweapon risks over immediate utility for standard medical or educational questions. For developers and researchers, this highlights a significant gap between raw model capability and public-facing deployment constraints in sensitive domains.

Sources coveringThe Verge, LessWrong

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Claude Fable won’t answer basic biology questions

The VergeJune 10, 20264 min read

Anthropic just released Claude Fable 5, calling it the most powerful AI model it has ever made widely available and praising its skills in biology, among others. But the model won't answer basic biology questions - the kind you'd expect a high schooler to handle. Instead, it hands off the query to the former flagship model, Claude Opus 4.8. It isn't because Fable doesn't know the answers. It's because Anthropic won't let it, by design. Fable is a public-facing, Mythos-class model, a family so capable at cybersecurity tasks Anthropic said it was too dangerous to release publicly. But while Anthropic has spent much of the extended Mythos rol … Read the full story at The Verge.

Anthropic just released Claude Fable 5, calling it the most powerful AI model it has ever made widely available and praising its skills in biology, among others. But the model won’t answer basic biology questions — the kind you’d expect a high schooler to handle. Instead, it hands off the query to the former flagship model, Claude Opus 4.8. It isn’t because Fable doesn’t know…

Excerpt shown under the publisher's RSS terms · 65 words · full text and figures are on the publisher's site

Read at The Verge ↗Ask about this article