~hyperlinks

Katie Moussouris, chief executive of cybersecurity firm Luta Security, said the jailbreak research was conducted by Amazon researchers who used a series of prompts to persuade Anthropic’s model to disclose information about several security vulnerabilities, according to the 

. Moussouris said Anthropic shared a copy of the report with her. She argued the information revealed by the model would be more useful to cybersecurity professionals defending networks than to malicious actors seeking to exploit them.

Politics_And_Law

Statement on the US government directive to suspend access to Fable5 and Mythos5

Scoresby

Jailbreakers were Amazon researchers.

> Katie Moussouris, chief executive of cybersecurity firm Luta Security, said the jailbreak research was conducted by Amazon researchers who used a series of prompts to persuade Anthropic’s model to disclose information about several security vulnerabilities, according to the *Wall Street Journal*. Moussouris said Anthropic shared a copy of the report with her. She argued the information revealed by the model would be more useful to cybersecurity professionals defending networks than to malicious actors seeking to exploit them.

source: https://www.washingtonexaminer.com/policy/technology/4607706/amazon-researcher-anthropic-ai-security-weaknesses/