Pinned Loading

1. emmy emmy Public

   Evaluation-invariant measurement for multi-agent AI systems.

   Python

2. pants-on-fire-eval pants-on-fire-eval Public

   Is the model lying or just wrong? Anti-scheming that targets both axes separately as model capabilities scale.

   Python

3. activation-tomography activation-tomography Public

   Natural language autoencoders as measurement instruments for AI safety applications. Research fork of kitft/natural_language_autoencoders.

   Python

4. paper-chase paper-chase Public

   multi-agent simulation of a scientific publishing ecosystem

   Python

5. micrograd-python micrograd-python Public

   An implementation of Karpathy's micrograd, as a basis for exploring the design decisions motivating the MLP architecture and gradient descent learning algorithm.

   Python

6. alexandria alexandria Public

   Minimalist infrastructure for maintaining a private collection of any sort, physical or digital.

   Python