Pinned Loading

1. how-bad-can-ai-be how-bad-can-ai-be Public

   Python

2. misalignment-by-default misalignment-by-default Public

   Python 2 1

3. DQN-maze-solver DQN-maze-solver Public

   Investigating whether or not RL agents can acausally collaborate with other instances of themselves.

   Python 1

4. transformer-shortest-paths transformer-shortest-paths Public

   Experimentally evaluating transformer's generalization on a synthetic task

   HTML 1

5. activation-steering-vs-prompting activation-steering-vs-prompting Public

   Is activation steering more powerful than prompting at mitigating deception in some current reasoning LLMs?

   Jupyter Notebook 1

6. theland theland Public

   theland

   JavaScript 2