Researcher disputes US government's characterization of Anthropic Fable 5 "jailbreak" as a simple code-fix prompt
By
Jessica Lyons
Summary
A security researcher reveals that the Trump administration's export ban on Anthropic's Fable 5 model was triggered by a simple three-word prompt ("Fix this code"), not a sophisticated jailbreak. Katie Moussouris, the only outside expert to read the research paper, disputes the government's characterization of the vulnerability and the national security rationale behind the export control directive.
Source
Hacker NewsResearcher disputes US government's characterization of Anthropic Fable 5 "jailbreak" as a simple code-fix prompttheregister.comKey quotes
· 3 pulledThe 'jailbreak' that prompted the Trump administration to block Anthropic's most advanced models was actually a simple three-word prompt: 'Fix this code.'
According to the one person who actually read the research paper
She says she was the only outside expert to read the third-party research paper on Fable 5 guardrail bypass techniques that prompted the ban.
You might also wanna read
Trump administration demands Anthropic fix jailbreak vulnerabilities in Claude Fable 5; experts say full prevention impossible
The Trump administration is pressuring Anthropic to fix jailbreak vulnerabilities in its Claude Fable 5 AI model before allowing its rerelea
wired.com·1d ago
Anthropic disables Fable 5 and Mythos 5 after U.S. export control order over jailbreak vulnerability
Anthropic disabled its new flagship AI models, Fable 5 and Mythos 5, after the U.S. government issued an export control order due to a disco
bit.ly·5d ago
U.S. Government Forces Anthropic to Shut Down Fable 5 and Mythos 5 AI Models Over National Security Concerns
The U.S. government has invoked emergency export control powers to force Anthropic to immediately suspend global access to its advanced AI m
undercodetesting.com·6d ago
US government orders Anthropic to disable Fable 5 and Mythos 5 AI models worldwide over security concerns
The US government has ordered Anthropic to disable global access to its most powerful AI models, Fable 5 and Mythos 5, citing national secur
the-decoder.com·6d ago
US Government Orders Anthropic to Block AI Models Fable 5 and Mythos 5 for Foreign Nationals Worldwide
The US government has issued an export control directive on national security grounds, ordering Anthropic to immediately suspend access to i
bigbreakingwire.in·6d ago
Anthropic halts Fable 5 and Mythos 5 AI models after US government directive, sparking European sovereign AI concerns
Anthropic halted access to its Fable 5 and Mythos 5 AI models after a Trump administration directive citing national security concerns over
euronews.com·4d ago