International AI Safety Report
Bengio, Yoshua, Mindermann, Sören, Privitera, Daniel, Besiroglu, Tamay, Bommasani, Rishi, Casper, Stephen, Choi, Yejin, Fox, Philip, Garfinkel, Ben, Goldfarb, Danielle, Heidari, Hoda, Ho, Anson, Kapoor, Sayash, Khalatbari, Leila, Longpre, Shayne, Manning, Sam, Mavroudis, Vasilios, Mazeika, Mantas, Michael, Julian, Newman, Jessica, Ng, Kwan Yee, Okolo, Chinasa T., Raji, Deborah, Sastry, Girish, Seger, Elizabeth, Skeadas, Theodora, South, Tobin, Strubell, Emma, Tramèr, Florian, Velasco, Lucia, Wheeler, Nicole, Acemoglu, Daron, Adekanmbi, Olubayo, Dalrymple, David, Dietterich, Thomas G., Felten, Edward W., Fung, Pascale, Gourinchas, Pierre-Olivier, Heintz, Fredrik, Hinton, Geoffrey, Jennings, Nick, Krause, Andreas, Leavy, Susan, Liang, Percy, Ludermir, Teresa, Marda, Vidushi, Margetts, Helen, McDermid, John, Munga, Jane, Narayanan, Arvind, Nelson, Alondra, Neppel, Clara, Oh, Alice, Ramchurn, Gopal, Russell, Stuart, Schaake, Marietje, Schölkopf, Bernhard, Song, Dawn, Soto, Alvaro, Tiedrich, Lee, Varoquaux, Gaël, Yao, Andrew, Zhang, Ya-Qin, Albalawi, Fahad, Alserkal, Marwan, Ajala, Olubunmi, Avrin, Guillaume, Busch, Christian, de Carvalho, André Carlos Ponce de Leon Ferreira, Fox, Bronwyn, Gill, Amandeep Singh, Hatip, Ahmet Halit, Heikkilä, Juha, Jolly, Gill, Katzir, Ziv, Kitano, Hiroaki, Krüger, Antonio, Johnson, Chris, Khan, Saif M., Lee, Kyoung Mu, Ligot, Dominic Vincent, Molchanovskyi, Oleksii, Monti, Andrea, Mwamanzi, Nusu, Nemer, Mona, Oliver, Nuria, Portillo, José Ramón López, Ravindran, Balaraman, Rivera, Raquel Pezoa, Riza, Hammam, Rugege, Crystal, Seoighe, Ciarán, Sheehan, Jerry, Sheikh, Haroon, Wong, Denise, Zeng, Yi
–arXiv.org Artificial Intelligence
I am honoured to present the International AI Safety Report. It is the work of 96 international AI experts who collaborated in an unprecedented effort to establish an internationally shared scientific understanding of risks from advanced AI and methods for managing them. We embarked on this journey just over a year ago, shortly after the countries present at the Bletchley Park AI Safety Summit agreed to support the creation of this report. Since then, we published an Interim Report in May 2024, which was presented at the AI Seoul Summit. We are now pleased to publish the present, full report ahead of the AI Action Summit in Paris in February 2025. Since the Bletchley Summit, the capabilities of general-purpose AI, the type of AI this report focuses on, have increased further. For example, new models have shown markedly better performance at tests of Professor Yoshua Bengio programming and scientific reasoning.
arXiv.org Artificial Intelligence
Jan-29-2025
- Country:
- Africa (1.00)
- Asia
- Middle East (1.00)
- South Korea > Seoul
- Seoul (0.24)
- Europe > United Kingdom
- England
- Buckinghamshire > Milton Keynes (0.24)
- Oxfordshire > Oxford (0.27)
- England
- North America
- Canada (1.00)
- United States
- California > Santa Clara County (0.27)
- New York > New York County
- New York City (0.28)
- Oceania (0.92)
- South America (1.00)
- Genre:
- Instructional Material > Course Syllabus & Notes (0.92)
- Overview (1.00)
- Personal (0.92)
- Questionnaire & Opinion Survey (1.00)
- Research Report
- Experimental Study (1.00)
- New Finding (1.00)
- Promising Solution (1.00)
- Workflow (0.92)
- Industry:
- Automobiles & Trucks (1.00)
- Banking & Finance
- Semiconductors & Electronics (0.92)
- Government
- Military > Cyberwarfare (0.67)
- Regional Government
- Asia Government (0.92)
- Europe Government (1.00)
- North America Government > United States Government (1.00)
- Media > News (1.00)
- Transportation > Air (1.00)
- Commercial Services & Supplies > Security & Alarm Services (0.92)
- Health & Medicine
- Consumer Health (1.00)
- Epidemiology (1.00)
- Pharmaceuticals & Biotechnology (1.00)
- Therapeutic Area
- Immunology (1.00)
- Infections and Infectious Diseases (1.00)
- Psychiatry/Psychology (1.00)
- Law
- Civil Rights & Constitutional Law (1.00)
- Criminal Law (1.00)
- Environmental Law (1.00)
- Intellectual Property & Technology Law (1.00)
- Energy
- Information Technology
- Hardware (0.92)
- Security & Privacy (1.00)
- Services (1.00)
- Education > Educational Setting (1.00)
- Telecommunications (0.92)
- Leisure & Entertainment (1.00)
- Social Sector (1.00)
- Law Enforcement & Public Safety > Crime Prevention & Enforcement (1.00)
- Water & Waste Management (0.92)
- Technology:
- Information Technology
- Artificial Intelligence
- Natural Language
- Chatbot (1.00)
- Generation (0.67)
- Large Language Model (1.00)
- Issues > Social & Ethical Issues (1.00)
- Vision (1.00)
- Speech (1.00)
- Cognitive Science > Problem Solving (1.00)
- History (1.00)
- Representation & Reasoning
- Agents (1.00)
- Expert Systems (0.92)
- Personal Assistant Systems (0.67)
- Scientific Discovery (0.65)
- Robots (1.00)
- Applied AI (1.00)
- Machine Learning
- Inductive Learning (0.67)
- Neural Networks > Deep Learning
- Generative AI (0.68)
- Pattern Recognition (0.92)
- Natural Language
- Communications
- Networks (1.00)
- Social Media (1.00)
- Web (1.00)
- Data Science
- Data Mining (1.00)
- Data Quality (1.00)
- Information Management > Search (1.00)
- Sensing and Signal Processing > Image Processing (1.00)
- Artificial Intelligence
- Information Technology