Maksym Andriushchenko max-andr

🚀

Pinned Loading

1. Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

   Python 518 59

2. OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents [NeurIPS 2025 Spotlight]

   Jupyter Notebook 69 6

3. Does Refusal Training in LLMs Generalize to the Past Tense? [ICLR 2025]

   Python 78 12

4. Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]

   Shell 393 47

5. JailbreakBench: An Open Robustness Benchmark for Jailbreaking Language Models [NeurIPS 2024 Datasets and Benchmarks Track]

   Python 654 76

6. RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

   Python 781 106