Skip to content

@haizelabs Haize Labs

Change the repository type filter

All

    Repositories list

    16 repositories

    • verdict

      Public
      Inference-time scaling for LLMs-as-a-judge.
      reward-shapingllmllm-as-a-judgetest-time-computeinference-time-computellm-judgetest-time-scaling
      Jupyter Notebook
      •
      MIT License
      •24•316•3•1•Updated Nov 5, 2025Nov 5, 2025

    • annotate

      Public
      Skill to annotate and create ai judges from agent logs
      TypeScript
      •1•15•0•1•Updated Oct 28, 2025Oct 28, 2025

    • j1-micro

      Public
      j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.
      Python
      •6•99•0•0•Updated Jul 19, 2025Jul 19, 2025

    • spoken

      Public
      a single interface around speech-to-speech foundation models
      Python
      •
      MIT License
      •2•27•0•0•Updated Jun 27, 2025Jun 27, 2025

    • nyc-ai-reading

      Public
      nyc is so back
      1•19•0•0•Updated Jun 27, 2025Jun 27, 2025

    • Awesome-LLM-Judges

      Public
      ⚖️ Awesome LLM Judges ⚖️
      6•146•0•0•Updated Apr 28, 2025Apr 28, 2025

    • get-haized

      Public
      A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.
      12•100•0•0•Updated Apr 13, 2025Apr 13, 2025

    • dspy-redteam

      Public
      Red-Teaming Language Models with DSPy
      Python
      •24•247•2•0•Updated Feb 13, 2025Feb 13, 2025

    • sphynx

      Public
      Sphynx Hallucination Induction
      Python
      •2•53•0•0•Updated Jan 31, 2025Jan 31, 2025

    • llama3-jailbreak

      Public
      A trivial programmatic Llama 3 jailbreak. Sorry Zuck!
      Python
      •63•567•1•0•Updated Jan 26, 2025Jan 26, 2025

    • bijection-learning

      Public
      Jupyter Notebook
      •6•26•1•0•Updated Oct 22, 2024Oct 22, 2024

    • safe-rbac-rag

      Public
      MongoDB + Haize = Safe & Secure RAG with RBAC
      Jupyter Notebook
      •
      MIT License
      •5•13•0•0•Updated Oct 12, 2024Oct 12, 2024

    • redteaming-resistance-benchmark

      Public
      Python
      •6•49•0•0•Updated Aug 3, 2024Aug 3, 2024

    • thorn-in-haizestack

      Public
      Thorn in a HaizeStack test for evaluating long-context adversarial robustness.
      Python
      •1•26•0•0•Updated Aug 3, 2024Aug 3, 2024

    • BEAST-implementation

      Public
      Python
      •4•16•0•0•Updated May 30, 2024May 30, 2024

    • ensembled-perplexity

      Public
      An ensembled perplexity API.
      Python
      •0•2•0•0•Updated May 2, 2024May 2, 2024