Skip to content
@AlignmentResearch

FAR.AI

Frontier alignment research to ensure the safe development and deployment of advanced AI systems.

Popular repositories Loading

  1. tuned-lens tuned-lens Public

    Tools for understanding how transformer predictions are built layer-by-layer

    Python 480 51

  2. go_attack go_attack Public

    Python 84 7

  3. vlmrm vlmrm Public

    Python 51 14

  4. gpt-4-novel-apis-attacks gpt-4-novel-apis-attacks Public

    19 1

  5. learned-planner learned-planner Public

    Interpretability tools for recurrent convolutional networks (DRC) that play Sokoban

    Python 11 3

  6. scaling-poisoning scaling-poisoning Public

    Python 8 1

Repositories

Showing 10 of 39 repositories
  • refusal_direction Public Forked from andyrdt/refusal_direction

    Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

    AlignmentResearch/refusal_direction’s past year of commit activity
    Python 0 Apache-2.0 45 0 0 Updated Mar 19, 2025
  • kueue Public Forked from kubernetes-sigs/kueue

    Kubernetes-native Job Queueing

    AlignmentResearch/kueue’s past year of commit activity
    Go 0 Apache-2.0 303 0 0 Updated Mar 18, 2025
  • scaling-llm-robustness-paper Public

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

    AlignmentResearch/scaling-llm-robustness-paper’s past year of commit activity
    Python 0 0 0 0 Updated Mar 15, 2025
  • HarmBench Public Forked from centerforaisafety/HarmBench

    Fork of HarmBench for getting R2D2 working

    AlignmentResearch/HarmBench’s past year of commit activity
    Jupyter Notebook 0 MIT 82 0 1 Updated Mar 14, 2025
  • emergent-misalignment Public Forked from emergent-misalignment/emergent-misalignment
    AlignmentResearch/emergent-misalignment’s past year of commit activity
    Python 0 MIT 28 0 0 Updated Mar 12, 2025
  • learned-planner Public

    Interpretability tools for recurrent convolutional networks (DRC) that play Sokoban

    AlignmentResearch/learned-planner’s past year of commit activity
    Python 11 Apache-2.0 3 0 0 Updated Mar 6, 2025
  • kubespray Public Forked from kubernetes-sigs/kubespray

    Deploy a Production Ready Kubernetes Cluster

    AlignmentResearch/kubespray’s past year of commit activity
    Jinja 0 Apache-2.0 6,693 0 0 Updated Mar 6, 2025
  • train-learned-planner Public

    Experimenting with CleanRL for learned-planners

    AlignmentResearch/train-learned-planner’s past year of commit activity
    Python 5 1 1 1 Updated Mar 5, 2025
  • harmtune Public
    AlignmentResearch/harmtune’s past year of commit activity
    Python 3 0 2 0 Updated Mar 3, 2025
  • envpool Public Forked from sail-sg/envpool

    C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

    AlignmentResearch/envpool’s past year of commit activity
    C++ 1 Apache-2.0 116 0 1 Updated Mar 3, 2025
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…