Skip to content
@METR

METR

Model Evaluation and Threat Research
README.md

Model Evaluation and Threat Research (METR)

METR is a research nonprofit that works on assessing whether cutting-edge AI systems could pose catastrophic risks to society.

We build the science of accurately assessing risks, so that humanity is informed before developing transformative AI systems.

Read more about our work here.

Our Software

Popular repositories Loading

  1. task-standard task-standard Public

    METR Task Standard

    TypeScript 135 32

  2. vivaria vivaria Public

    Vivaria is METR's tool for running evaluations and conducting agent elicitation research.

    TypeScript 74 22

  3. public-tasks public-tasks Public

    TeX 72 3

  4. ai-rd-tasks ai-rd-tasks Public

    Python 51 6

  5. task-template task-template Public template

    TypeScript 9 5

  6. autonomy-evals-guide autonomy-evals-guide Public

    SCSS 3 4

Repositories

Showing 10 of 18 repositories
  • vivaria Public

    Vivaria is METR's tool for running evaluations and conducting agent elicitation research.

    METR/vivaria’s past year of commit activity
    TypeScript 74 MIT 22 227 (3 issues need help) 16 Updated Jan 12, 2025
  • public-plots Public

    Public repository containing METR's DVC pipeline for plot generation

    METR/public-plots’s past year of commit activity
    Python 0 0 0 0 Updated Jan 11, 2025
  • SWE-bench-fork Public Forked from swe-bench/SWE-bench

    [ICLR 2024] SWE-bench: Can Language Models Resolve Real-world Github Issues?

    METR/SWE-bench-fork’s past year of commit activity
    Python 0 MIT 397 0 1 Updated Jan 11, 2025
  • viv-task-dev Public
    METR/viv-task-dev’s past year of commit activity
    Shell 0 1 7 0 Updated Jan 10, 2025
  • public-tasks Public
    METR/public-tasks’s past year of commit activity
    TeX 72 3 0 2 Updated Jan 9, 2025
  • ai-rd-tasks Public
    METR/ai-rd-tasks’s past year of commit activity
    Python 51 6 1 2 Updated Jan 9, 2025
  • task-standard Public

    METR Task Standard

    METR/task-standard’s past year of commit activity
    TypeScript 135 MIT 32 6 3 Updated Jan 3, 2025
  • worktest-sw-eng-deps Public
    METR/worktest-sw-eng-deps’s past year of commit activity
    Dockerfile 0 0 0 0 Updated Dec 29, 2024
  • task-assets Public
    METR/task-assets’s past year of commit activity
    Python 0 0 0 0 Updated Dec 28, 2024
  • task-protected-scoring Public
    METR/task-protected-scoring’s past year of commit activity
    Python 0 1 3 2 Updated Dec 13, 2024
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…