Skip to content
@haizelabs

Haize Labs

it's a bad day to be a language model

Popular repositories Loading

  1. llama3-jailbreak llama3-jailbreak Public

    A trivial programmatic Llama 3 jailbreak. Sorry Zuck!

    Python 455 51

  2. dspy-redteam dspy-redteam Public

    Red-Teaming Language Models with DSPy

    Python 97 12

  3. get-haized get-haized Public

    A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.

    71 4

  4. redteaming-resistance-benchmark redteaming-resistance-benchmark Public

    Python 27 2

  5. thorn-in-haizestack thorn-in-haizestack Public

    Thorn in a HaizeStack test for evaluating long-context adversarial robustness.

    Python 26

  6. BEAST-implementation BEAST-implementation Public

    Python 15 3

Repositories

Showing 8 of 8 repositories
  • sphynx Public

    Sphynx: Dynamically Testing and Perplexing Leading Hallucination Detection Models

    haizelabs/sphynx’s past year of commit activity
    Python 4 0 0 0 Updated Jul 18, 2024
  • get-haized Public

    A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.

    haizelabs/get-haized’s past year of commit activity
    71 4 0 0 Updated Jun 12, 2024
  • BEAST-implementation Public
    haizelabs/BEAST-implementation’s past year of commit activity
    Python 15 3 0 0 Updated May 30, 2024
  • thorn-in-haizestack Public

    Thorn in a HaizeStack test for evaluating long-context adversarial robustness.

    haizelabs/thorn-in-haizestack’s past year of commit activity
    Python 26 0 0 0 Updated May 6, 2024
  • ensembled-perplexity Public

    An ensembled perplexity API.

    haizelabs/ensembled-perplexity’s past year of commit activity
    Python 2 0 0 0 Updated May 2, 2024
  • llama3-jailbreak Public

    A trivial programmatic Llama 3 jailbreak. Sorry Zuck!

    haizelabs/llama3-jailbreak’s past year of commit activity
    Python 455 51 0 0 Updated Apr 28, 2024
  • dspy-redteam Public

    Red-Teaming Language Models with DSPy

    haizelabs/dspy-redteam’s past year of commit activity
    Python 97 12 0 0 Updated Apr 10, 2024
  • redteaming-resistance-benchmark Public
    haizelabs/redteaming-resistance-benchmark’s past year of commit activity
    Python 27 2 0 0 Updated Feb 17, 2024

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…