Skip to content
@haizelabs

Haize Labs

build ai systems you can trust.

Popular repositories Loading

  1. llama3-jailbreak llama3-jailbreak Public

    A trivial programmatic Llama 3 jailbreak. Sorry Zuck!

    Python 573 65

  2. verdict verdict Public

    Inference-time scaling for LLMs-as-a-judge.

    Jupyter Notebook 348 31

  3. dspy-redteam dspy-redteam Public

    Red-Teaming Language Models with DSPy

    Python 275 32

  4. Awesome-LLM-Judges Awesome-LLM-Judges Public

    ⚖️ Awesome LLM Judges ⚖️

    202 15

  5. j1-micro j1-micro Public

    j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.

    Python 108 7

  6. get-haized get-haized Public

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

    99 12

Repositories

Showing 10 of 21 repositories
  • tourno Public

    TournO (Tournament Optimization) combines pointwise and pairwise LLM judges to produce reward signals for RLHF, using tournament-style comparisons (round-robin, ELO) to derive scalar rewards from pairwise preferences.

    haizelabs/tourno's past year of commit activity
    Python 13 MIT 0 0 3 Updated May 8, 2026
  • EvoForge Public
    haizelabs/EvoForge's past year of commit activity
    Python 39 4 0 0 Updated Apr 15, 2026
  • skills Public

    Haize Labs Skills

    haizelabs/skills's past year of commit activity
    HTML 0 0 0 0 Updated Apr 10, 2026
  • calligraphy Public
    haizelabs/calligraphy's past year of commit activity
    1 0 0 0 Updated Apr 10, 2026
  • prime-rl Public Forked from PrimeIntellect-ai/prime-rl

    Async RL Training at Scale

    haizelabs/prime-rl's past year of commit activity
    Python 0 Apache-2.0 464 0 0 Updated Jan 1, 2026
  • verdict Public

    Inference-time scaling for LLMs-as-a-judge.

    haizelabs/verdict's past year of commit activity
    Jupyter Notebook 348 MIT 31 3 3 Updated Nov 5, 2025
  • annotate Public

    Skill to annotate and create ai judges from agent logs

    haizelabs/annotate's past year of commit activity
    TypeScript 17 1 0 1 Updated Oct 28, 2025
  • j1-micro Public

    j1-micro (1.7B) & j1-nano (600M) are absurdly tiny but mighty reward models.

    haizelabs/j1-micro's past year of commit activity
    Python 108 7 0 0 Updated Jul 19, 2025
  • spoken Public

    a single interface around speech-to-speech foundation models

    haizelabs/spoken's past year of commit activity
    Python 28 MIT 2 0 0 Updated Jun 27, 2025
  • nyc-ai-reading Public

    nyc is so back

    haizelabs/nyc-ai-reading's past year of commit activity
    21 1 0 0 Updated Jun 27, 2025
View all repositories

Most used topics

Loading…