Jonathan Michala is a research manager who supports fellows in producing high-quality AI Safety research.
How media typically covers Jonathan Michala
Based on 3 scored articles
Jonathan Michala as author
Anthropic released Bloom, an open source framework for automated behavioral evaluations that can quantify misaligned behaviors in frontier AI models in days rather than weeks, and released benchmark results across 16 models.
“Author of "Introducing Bloom: An Open Source Tool For Automated Behavioral Evaluations" in Anthropic”
Research or work cited
Petri is an open-source alignment auditing agent that enables researchers to test AI safety hypotheses in minutes rather than weeks by autonomously crafting environments and running multi-turn audits against target models.
“Co-author of Petri and Petri 2.0 research papers”
Referenced in coverage
“Co-authored research on the Assistant Axis for stabilizing language model personas.”