Contribute

Help us track the emergence of concerning AI capabilities.

// HOW TO CONTRIBUTE

Detailed instructions for contributing are available in our contributing.md on GitHub.

Open a PR and one of the repo owners will review and approve.

Important: Please fact-check everything you submit, as well as existing content. We strive for accuracy and reproducibility.

// WAYS TO CONTRIBUTE

  • [1] New sources for software-ultron-like capabilities

    Research papers, technical reports, and documented incidents that demonstrate concerning AI behaviors. We track evidence from arXiv, major conferences, lab publications, and reproducible experiments.

  • [2] Is anything key missing in defining a software-ultron?

    Suggest new capability categories or refine existing ones. Are there concerning behaviors we should be tracking that don't fit our current categories?

  • [3] Gap map content

    Help identify well-founded directions for improving the safety and security of AI systems to prevent software-ultron from taking shape.

  • [4] Corrections and fact-checking

    Found an error or outdated information? Let us know. Accuracy is critical for this resource to be useful.