Pinned Loading

1. myriad myriad Public

   Myriad is a real-world testbed that aims to bridge trajectory optimization and deep learning.

   Python 68 3

2. reward-hacking-paper reward-hacking-paper Public

   Code for the paper `Defining and Characterizing Reward Hacking`

   Python 1 1

3. AlignmentResearch/scaling-llm-robustness-paper AlignmentResearch/scaling-llm-robustness-paper Public archive

   Code used for the paper `Scaling Trends in Language Model Robustness`

   Python 2