Popular repositories Loading

1. llama3-jailbreak llama3-jailbreak Public

   A trivial programmatic Llama 3 jailbreak. Sorry Zuck!

   Python 450 51

2. dspy-redteam dspy-redteam Public

   Red-Teaming Language Models with DSPy

   Python 97 12

3. get-haized get-haized Public

   A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.

   71 4

4. redteaming-resistance-benchmark redteaming-resistance-benchmark Public

   Python 27 2

5. thorn-in-haizestack thorn-in-haizestack Public

   Thorn in a HaizeStack test for evaluating long-context adversarial robustness.

   Python 26

6. BEAST-implementation BEAST-implementation Public

   Python 15 3