ended7월 10일· 1 sources

Anthropic wants to grade AI jailbreaks like CVEs. Here's the framework.

Why it matters

Anthropic has re-deployed Claude Fable 5 and used the moment to publish something the industry has been missing: a structured framework for talking about how dangerous an AI jailbreak actually is. Thi...

1
Sources
+0
24h
Growth
72d
Active

Sources

Related Issues