Cohort Size
31 July - 9 August 2023
9 days

ML4Good expands internationally!

We recently held the third edition of the ML4Good AI safety research training bootcamp at the beginning of August! We are now in the midst of preparations for an ML4Good event, which has already started in Germany and will be held in Switzerland in early September. Our participants, who come from a variety of backgrounds, are extremely enthusiastic about the idea of supporting and spreading this training camp model throughout Europe!


No items found.


Edoardo Pona
Head of AI, Serac Tech
Edoardo is doing research in interpretability, and works with aisafety camp.
Bogdan-Ionut Cirstea
Conceptual Teacher
Bogdan is an independent AI safety researcher funded by the Center on Long-Term Risk currently working mostly at the intersection of neuroscience, deep learning and AI alignment. During the camp, he will be the main instructor in charge of the conceptual parts. He completed a Master’s degree in Applied Mathematics at the École normale supérieure and has a PhD in Machine Learning.
Jonathan Claybrough
Governance and strategy TA
Jonathan shifted to full-time involvement in AI safety around late 2022 from a background in networks and software engineering, Since then, he has contributed to technical standards for the EU AI Act, delivered introductory talks on AI safety, co-founded the European Network for AI Safety (ENAIS), and worked on AI threat models and risk reduction.