Anthropic Proposes CVE-Style Severity Scale to Standardize AI Jailbreak Risk
Anthropic has introduced the Cyber Jailbreak Severity (CJS) scale, a five-tier framework ranging from CJS-0 (informational, no real threat) to CJS-4 (critical, expert-level attack enablement)…
Read the full articleYou might also wanna read
Trump administration demands Anthropic fix jailbreak vulnerabilities in Claude Fable 5; experts say full prevention impossible
Trump administration officials tell WIRED that if Anthropic wants to rerelease Fable 5, it will need to ensure the model's guardrails can't
wired.com·22d ago
Researcher Claims to Jailbreak Anthropic's Claude Fable 5 Within 48 Hours of Launch
A researcher claims he has already bypassed Claude Fable 5’s safety filters, exposing flaws in Anthropic’s guardrail system using multi-step
cointelegraph.com·28d ago
Anthropic Releases Claude Fable 5 with Tiered Safeguards for High-Risk Requests
Anthropic has made Claude Fable 5 generally available, positioning it as a powerful Mythos-class AI model with built-in safeguards that down
hendryadrian.com·28d ago
Anthropic Releases Claude Mythos AI Model Despite Crypto Community Concerns Over Vulnerability Exploitation
Crypto users are warning others to review their exposure to protocols after Anthropic released a public version of Claude Mythos, an AI mode
cointelegraph.com·29d ago
Anthropic disables Fable 5 and Mythos 5 after U.S. export control order over jailbreak vulnerability
Anthropic calls the export-control order a "misunderstanding" over minor vulnerabilities. The White House says the company put its consumer
thenewstack.io·26d ago
Anthropic restores Claude Fable 5 after 19-day shutdown triggered by Amazon jailbreak report
On June 12, Amazon engineers handed a report to the U.S.
bit.ly·6d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.