Skip to content

@centerforaisafety centerforaisafety

Change the repository type filter

All

    Repositories list

    29 repositories

    • wellbeing

      Public
      Measuring and improving the functional pleasure and pain of AIs
      MIT License
      •1•0•0•0•Updated Apr 27, 2026Apr 27, 2026

    • cerberus-cluster

      Public
      HPC cluster code and configurations for running on OCI
      Python
      •
      Universal Permissive License v1.0
      •2•9•59•2•Updated Mar 26, 2026Mar 26, 2026

    • simple-llm-api

      Public
      Python
      •
      MIT License
      •0•0•0•0•Updated Mar 24, 2026Mar 24, 2026

    • ccc-docs

      Public
      CAIS Compute Cluster (CCC) documentation
      MIT License
      •0•3•7•0•Updated Feb 20, 2026Feb 20, 2026

    • hle

      Public
      Humanity's Last Exam
      Python
      •
      MIT License
      •97•1.5k•4•3•Updated Feb 20, 2026Feb 20, 2026

    • course.mlsafety.org

      Public
      HTML
      •
      MIT License
      •0•3•0•0•Updated Jan 28, 2026Jan 28, 2026

    • simple-evals

      Public
      Simple evaluation scripts for AI benchmarks with minimal dependencies.
      Python
      •
      MIT License
      •1•13•0•0•Updated Dec 17, 2025Dec 17, 2025

    • neurips-2025-social

      Public
      0•0•0•0•Updated Dec 4, 2025Dec 4, 2025

    • textquests

      Public
      ZAP
      •
      MIT License
      •5•18•1•3•Updated Dec 2, 2025Dec 2, 2025

    • rli_evaluation_platform

      Public
      Public repository for the Remote Labor Index (RLI)
      TypeScript
      •4•66•1•0•Updated Nov 3, 2025Nov 3, 2025

    • forecasting

      Public
      Forecasting.
      TypeScript
      •
      MIT License
      •11•37•2•0•Updated Aug 2, 2025Aug 2, 2025

    • prometheus-slurm-exporter

      Public
      Prometheus exporter for performance metrics from Slurm.
      Go
      •
      GNU General Public License v3.0
      •182•3•5•1•Updated Jun 16, 2025Jun 16, 2025

    • wmdp

      Public
      WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning method which reduces LLM…
      Jupyter Notebook
      •
      MIT License
      •43•167•12•3•Updated May 29, 2025May 29, 2025

    • AISES

      Public
      CSS
      •3•2•0•0•Updated Apr 24, 2025Apr 24, 2025

    • cluster-docs-old

      Public archive
      CSS
      •
      MIT License
      •2•1•4•0•Updated Apr 10, 2025Apr 10, 2025

    • slurm-job-exporter

      Public
      Prometheus exporter for the stats in the cgroup accounting with slurm. This will also collect stats of a job using NVIDIA GPUs.
      Python
      •
      Apache License 2.0
      •23•1•0•0•Updated Apr 10, 2025Apr 10, 2025

    • mask

      Public
      Code for evaluating AI systems on the MASK honesty benchmark.
      Python
      •
      MIT License
      •14•20•1•0•Updated Mar 6, 2025Mar 6, 2025

    • emergent-values

      Public
      Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"
      Jupyter Notebook
      •
      MIT License
      •23•90•2•0•Updated Feb 27, 2025Feb 27, 2025

    • safetywashing

      Public
      Measuring correlations between safety benchmarks and general AI capabilities benchmarks.
      Python
      •
      MIT License
      •3•11•0•0•Updated Oct 2, 2024Oct 2, 2024

    • HarmBench

      Public
      HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
      Jupyter Notebook
      •
      MIT License
      •139•936•30•5•Updated Aug 16, 2024Aug 16, 2024

    • tdc2023-starter-kit

      Public
      This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.
      trojanredteamingneurips-2023
      trojanredteamingneurips-2023tdc-2023
      Python
      •
      MIT License
      •27•91•0•0•Updated May 19, 2024May 19, 2024

    • safety_challenge

      Public
      HTML
      •
      MIT License
      •0•0•0•0•Updated Mar 28, 2024Mar 28, 2024

    • trojan-dc-2023

      Public
      JavaScript
      •
      MIT License
      •0•1•1•0•Updated Mar 6, 2024Mar 6, 2024

    • adversarial-corruptions

      Public
      Jupyter Notebook
      •0•4•0•0•Updated Oct 30, 2023Oct 30, 2023

    • reading

      Public
      1•1•0•0•Updated Oct 26, 2023Oct 26, 2023

    • AIS-cost-effectiveness

      Public
      Cost-effectiveness models, tools, and results for various AI safety field-building programs.
      Python
      •
      MIT License
      •4•6•0•2•Updated Aug 15, 2023Aug 15, 2023

    • trojan-dc-2022

      Public
      Website for the Trojan Detection Challenge NeurIPS 2022 competition
      JavaScript
      •
      MIT License
      •0•0•0•0•Updated Jul 28, 2023Jul 28, 2023

    • goslmailer

      Public
      GoSlurmMailer - drop in replacement for default slurm MailProg. Delivers slurm job messages to various destinations.
      Go
      •6•0•0•0•Updated Jun 21, 2023Jun 21, 2023

    • Intro_to_ML_Safety

      Public
      27•77•0•0•Updated May 31, 2023May 31, 2023
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.