Key Concepts in AI Safety: Specification in Machine Learning (Tim G. J. Rudner, Helen Toner, CSET)

January 1, 2022

This paper is the fourth installment in a series on “AI safety,” an area of machine learning research that aims to identify causes of unintended behavior in machine learning systems and develop tools to ensure these systems work safely and reliably. The first paper in the series, “Key Concepts in AI Safety: An Overview,” outlined three categories of AI safety issues—problems of robustness, assurance, and specification—and the subsequent two papers described problems of robustness and assurance, respectively. This paper introduces specification as a key element in designing modern machine learning systems that operate as intended.

Key Concepts in AI Safety: Specification in Machine Learning – Center for Security and Emerging Technology (georgetown.edu)

Marco Emanuele

Marco Emanuele è appassionato di cultura della complessità, cultura della tecnologia e relazioni internazionali. Approfondisce il pensiero di Hannah Arendt, Edgar Morin, Raimon Panikkar. Marco ha insegnato Evoluzione della Democrazia e Totalitarismi, è l’editor di The Global Eye e scrive per The Science of Where Magazine. Marco Emanuele is passionate about complexity culture, technology culture and international relations. He delves into the thought of Hannah Arendt, Edgar Morin, Raimon Panikkar. He has taught Evolution of Democracy and Totalitarianisms. Marco is editor of The Global Eye and writes for The Science of Where Magazine.

Key Concepts in AI Safety: Specification in Machine Learning (Tim G. J. Rudner, Helen Toner, CSET)

The Other AI Race: An Export Promotion Strategy for the Global South (Marianne Lu and Sam Winter-Levy – Carnegie Endowment for International Peace)

Tariffs on Copper Imports Will Affect 45 Percent of U.S. Copper Needs (Ryan C. Berg, Christopher Hernandez-Roy, and Henry Ziemer – Center for Strategic...

Ukraine’s Economic Struggles Signal Barriers to Post-War Recovery (Tamerlan Vahabov – The Jamestown Foundation)

Moscow Opens Door to Widespread Digital Surveillance (Hlib Parfonov – The Jamestown Foundation)

Moscow and Tehran Working to Block U.S. Involvement in Zangezur Corridor (Paul Globe – The Jamestown Foundation)

Inside the Israeli government’s starvation of Gaza, from an aid group trying to deliver food (Arwa Damon – Atlantic Council)

Forget Berlin and Paris — Athens Is Leading Europe’s Digital Shift (Konstantinos Komaitis – Tech Policy Press)

Governments Want to Ease AI Regulation for Innovation, But Do Citizens Agree? (Natali Helberger, Sophie Morosoli, Nicolas Mattis, Laurens Naudts, Claes H. de Vreese...

Lethal Autonomous Weapons and the ‘Right for Machine Hesitation’ (Virgílio Almeida, Ricardo Fabrino Mendonça, Fernando Filgueiras – Tech Policy Press)