Dane Sherrets
@DaneSherrets
One of my favorite projects last year was working on the @Hacker0x01 team that facilitated this testing.
Watch this space.
Watch this space.
Anthropic@AnthropicAI · Feb 3, 2025We challenged jailbreakers to try to break a prototype version of the system to test its robustness.
After thousands of hours of red teaming, not one participant found a reliable jailbreak that extracted detailed information across a set of 10 harmful questions.
Open quoted post →After thousands of hours of red teaming, not one participant found a reliable jailbreak that extracted detailed information across a set of 10 harmful questions.
0 2