Asset Details

MbrlCatalogueTitleDetail

Do you wish to reserve the book?

The Singapore Consensus on Global AI Safety Research Priorities

by Ong, Luke , Kantamneni, Subhash , Xu, Wei , Žikelić, Djordje , Prud'Homme, Benjamin , Balachandran, Vidhisha , Petrie, James , Ortega, Alejandro , Kamphuis, Meindert , Lu, Chaochao , Kankanhalli, Mohan , Nushi, Besmira , Bryan Low Kian Hsiang , Lee, Taewhi , Sanchez-Pi, Nayat , Cass-Beggs, Duncan , Zeng, Yi , Bello, Imane , Li, Xiaojian , Jawhar, Sami , Russell, Stuart , Trager, Robert , Belinsky, Michael , Soto, Martín , Heidecke, Johannes , Maharaj, Tegan , Chen, Jiahao , Ng, Kwan Yee , Fan, Jinyu , Anthony Tung K H , Huang, Minlie , Dai, Juntao , Nitzberg, Mark , Peigné, Pierre , Zhang, HongJiang , Campos, Siméon , Eiras, Francisco , hÉigeartaigh, Seán O , Siddiqui, Saad , Kwa, Thomas , Engels, Joshua , Hendrycks, Dan , Tse, Brian , Mai, Yifan , Moës, Nick , Mindermann, Sören , Dziri, Nouha , Julian, Michael , Tan, Cheston , Mathias Bonde Kirk , Nam, Kihyuk , Song, Dawn , Gleave, Adam , Kwok-Yan, Lam , Buck Shlegeris , Goodman, Noah , Lee, Wan Sie , Ladish, Jeffrey , Liu, Jiajun , Wang, Jingyu , Casper, Stephen , Ya-Qin, Zhang , Hodes, Cyrus , Sinha, Aradhana , Delaborde, Agnes , Malo Bourgon , Fynn Heide , Mallah, Richard , Dong Ting , Barez, Fazl , Brakel, Mark , Chowdhury, Rumman , Kalai, Ad

in Priorities / Trustworthiness

2025

Yes Please

Hey, we have placed the reservation for you!

By the way, why not check out events that you can attend while you pick your title.

Oops! Something went wrong.

Looks like we were not able to place the reservation. Kindly try again later.

Are you sure you want to remove the book from the shelf?

The Singapore Consensus on Global AI Safety Research Priorities

in Priorities / Trustworthiness

2025

Confirm

Do you wish to request the book?

The Singapore Consensus on Global AI Safety Research Priorities

in Priorities / Trustworthiness

2025

Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy

How would you like to get it?

Submit

We have requested the book for you!

Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.

Oops! Something went wrong.

Looks like we were not able to place your request. Kindly try again later.

Paper

The Singapore Consensus on Global AI Safety Research Priorities

Ong, Luke,

Kantamneni, Subhash,

Xu, Wei,

Žikelić, Djordje,

Prud'Homme, Benjamin,

Balachandran, Vidhisha,

Petrie, James,

Ortega, Alejandro,

Kamphuis, Meindert,

Lu, Chaochao,

Kankanhalli, Mohan,

Nushi, Besmira,

Bryan Low Kian Hsiang,

Lee, Taewhi,

Sanchez-Pi, Nayat,

Cass-Beggs, Duncan,

Zeng, Yi,

Bello, Imane,

Li, Xiaojian,

Jawhar, Sami,

Russell, Stuart,

Trager, Robert,

Belinsky, Michael,

Soto, Martín,

Heidecke, Johannes,

Maharaj, Tegan,

Chen, Jiahao,

Ng, Kwan Yee,

Fan, Jinyu,

Anthony Tung K H,

Huang, Minlie,

Dai, Juntao,

Nitzberg, Mark,

Peigné, Pierre,

Zhang, HongJiang,

Campos, Siméon,

Eiras, Francisco,

hÉigeartaigh, Seán O,

Siddiqui, Saad,

Kwa, Thomas,

Engels, Joshua,

Hendrycks, Dan,

Tse, Brian,

Mai, Yifan,

Moës, Nick,

Mindermann, Sören,

Dziri, Nouha,

Julian, Michael,

Tan, Cheston,

Mathias Bonde Kirk,

Nam, Kihyuk,

Song, Dawn,

Gleave, Adam,

Kwok-Yan, Lam,

Buck Shlegeris,

Goodman, Noah,

Lee, Wan Sie,

Ladish, Jeffrey,

Liu, Jiajun,

Wang, Jingyu,

Casper, Stephen,

Ya-Qin, Zhang,

Hodes, Cyrus,

Sinha, Aradhana,

Delaborde, Agnes,

Malo Bourgon,

Fynn Heide,

Mallah, Richard,

Dong Ting,

Barez, Fazl,

Brakel, Mark,

Chowdhury, Rumman,

Kalai, Ad

2025

Overview

Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy, reliable, and secure. Building a trusted ecosystem is therefore essential -- it helps people embrace AI with confidence and gives maximal space for innovation while avoiding backlash. The \"2025 Singapore Conference on AI (SCAI): International Scientific Exchange on AI Safety\" aimed to support research in this space by bringing together AI scientists across geographies to identify and synthesise research priorities in AI safety. This resulting report builds on the International AI Safety Report chaired by Yoshua Bengio and backed by 33 governments. By adopting a defence-in-depth model, this report organises AI safety research domains into three types: challenges with creating trustworthy AI systems (Development), challenges with evaluating their risks (Assessment), and challenges with monitoring and intervening after deployment (Control).

Share this book

Add to My Shelf

Publisher

Cornell University Library, arXiv.org

Subject

Priorities

/ Trustworthiness