Pinned Loading

1. Second-Order-Jailbreak Second-Order-Jailbreak Public

   NeurIPS workshop : We examine the risk of powerful malignant intelligent actors spreading their influence over networks of agents with varying intelligence and motivations.

   Python 5

2. red-teamer-mistral-nemo red-teamer-mistral-nemo Public

   Finetuning of Mistral Nemo 13B on the WildJailbreak dataset to produce a red-teaming model

   Python 2

3. llm-as-a-jailbreak-judge llm-as-a-jailbreak-judge Public

   Explore techniques to use small models as jailbreaking judges

   Python 1

4. token-noise-sandbagging token-noise-sandbagging Public

   Detection of sandbagging through Best-of-N sampling with input-level noise perturbations

   Python 1

5. relax relax Public

   Implementation of ML papers in JAX+Haiku+Optax while being relaxed

   Jupyter Notebook

6. stockBot stockBot Public

   stockBot is a gentle automatic trader bot

   Python 17 9