HackTalk: Miguel A. Peñaloza - AI4Math Challenge and a path into AI safety
HackTalk: Miguel A. Peñaloza
AI4Math Challenge and a path into AI safety
Pre-hackathon talk for the Global South AI Safety Hackathon, June 19-21 online. Free and open.
Miguel A. Peñaloza is a professional statistician whose work focuses on developing benchmarks to assess the capabilities of Large Language Models (LLMs). Currently, he is designing methodologies aimed at making AI system evaluations more inclusive, representative, and globally accessible.
His talk covers the AI4Math Challenge benchmark and his path into AI safety.
Format: ~15-20 min talk + Q&A. Talk in Spanish. Online (Zoom), livestreamed and recorded.
Part of the Global South AI Safety Hackathon, June 19-21, online with in-person hubs across Latin America, Africa, and Asia. Organized by Apart Research.