Popular repositories Loading

1. adversarial_prompting adversarial_prompting Public

   Python 53 5

2. incontext_influences incontext_influences Public

   In-context Example Selection with Influences

   Python 15 1

3. Meerkat Meerkat Public

   An agent for auditing repositories of traces for violations of safety properties. Automatically finds cheating (task-level gaming and harness-level cheating) on top benchmarks.

   Python 15 3

4. InstABoost InstABoost Public

   Instruction Following by Boosting Attention of Large Language Models

   Jupyter Notebook 8 1

5. ares ares Public

   Official repository for "Probabilistic Soundness Guarantees in LLM Reasoning Chains"

   Jupyter Notebook 6 1

6. sqrl sqrl Public

   Python 5