MATS 学员:
Isha Gupta
作者:
Isha Gupta, Kai Fronsdal, Abhay Sheshadri, Jonathan Michala, Jacqueline Tay, Rowan Wang, Samuel R. Bowman, Sara Price
引用次数
摘要:
We are releasing Bloom, an agentic framework for developing behavioral evaluations. Bloom's evaluations are reproducible and targeted: unlike open-ended auditing, Bloom takes a researcher-specified behavior and quantifies its frequency and severity across automatically generated scenarios. Bloom's evaluations correlate strongly with our hand-labelled judgments and reliably separate baseline models from intentionally misaligned ones. As examples, we also release benchmark results for four alignment relevant behaviors on 16 models. Bloom is available at github.com/safety-research/bloom.
MATS 是一个独立的研究与教育项目,致力于连接新兴研究人员与 AI 对齐、治理和安全领域的导师。
每期 MATS 项目在加州伯克利进行,为期 12 周。部分学员可选择之后前往伦敦参加为期 6 至 12 个月的延伸项目。