人工智能的场景应用及其对社会治理的新挑战，注意场景应用和社会治理的对应，同时突出新挑战

1.1.Artificial intelligence(AI)is already delivering wide societal benefits,from medical advances1 to mitigating climate change.2 For example,an AI technology developed by DeepMind,a UKbased business,can now predict the structure of almost every protein known to science.3 This breakthrough will accelerate scientific research and the development of life-saving medicines–it has already helped scientists to make huge progress in combating malaria,antibiotic resistance,and plastic waste.2.2.The UK Science and Technology Framework4 sets out government’s strategic vision and identifies AI as one of five critical technologies.The framework notes the role of regulation in creating the environment for AI to flourish.We know that we have yet to see AI technologies reach their full potential.Under the right conditions,AI will transform all areas of life5 and stimulate the UK economy by unleashing innovation and driving productivity,6 creating new jobs and improving the workplace.3.3.Across the world,countries and regions are beginning to draft the rules for AI.The UK needs to act quickly to continue to lead the international conversation on AI governance and demonstrate the value of our pragmatic,proportionate regulatory approach.The need to act was highlighted by Sir Patrick Vallance in his recent Regulation for Innovation review.The report identifies the short time frame for government intervention to provide a clear,pro-innovation regulatory environment in order to make the UK one of the top places in the world to build foundational AI companies.74.4.While we should capitalise on the benefits of these technologies,we should also not overlook the new risks that may arise from their use,nor the unease that the complexity of AI technologies can produce in the wider public.We already know that some uses of AI could1The use of AI in healthcare and medicine is booming,Insider Intelligence,2023.2 How to fight climate change using AI,Forbes,2022;Tackling Climate Change with Machine Learning,Rolnick et al.,2019.

(1)IN GENERAL.—The Director shall award 15 grants for research on artificial(F)fields and research areas that will con18 tribute to the development and deployment of 19 trustworthy artificial intelligence systems,in20 cluding—21(i)algorithmic explainability;22(ii)methods to assess,characterize,23 and reduce bias in datasets and artificial 24 intelligence systems;and 25VerDate Sep 11 2014 23:31 Mar 25,2020 Jkt 099200 PO 00000 Frm 00039 Fmt 6652 Sfmt 6201 E:\BILLS\H6216.IH H6216pamtmann on DSKBC07HB2PROD with BILLS40•HR 6216 IH(iii)safety and robustness of artificial 1 intelligence systems,including assurance,2 verification,validation,security,and con3 trol;4(G)privacy and security,including for 5 datasets used for the training and inference of 6 artificial intelligence systems,and software and 7 hardware used in artificial intelligence systems;8(H)fields and research areas that address 9 the application of artificial intelligence systems 10 to scientific discovery and societal challenges;11(I)societal,ethical,safety,education,12 workforce,and security implications of artificial 13 intelligence systems,including social impact of 14 artificial intelligence systems on different 15 groups within society,especially historically 16 marginalized groups;and 17(J)qualitative and quantitative forecasting 18 of future capabilities,applications,and impacts.19

1.34.The proposed regulatory framework does not seek to address all of the wider societal and global challenges that may relate to the development or use of AI.This includes issues relating to access to data,compute capability,and sustainability,as well as the balancing of the rights of content producers and AI developers.These are important issues to consider–especially in the context of the UK’s ability to maintain its place as a global leader in AI–but they are outside of the scope of our proposals for a new overarching framework for AI regulation.2.35.Government is taking wider action to ensure the UK retains its status as a global leader in AI,for example by taking forward Sir Patrick Vallance’s recommendation relating to intellectual property law and generative AI.77 This will ensure we keep the right balance between protecting rights holders and our thriving creative industries,while supporting AI developers to access the data they need.75 Trust in Artificial Intelligence:a five country study,KPMG and the University of Queensland,2021;Evidence to support the analysis of impacts for AI governance,Frontier Economics,2023.76“Building on the UK’s strengths in the professional services and technology sectors,AI assurance will also become a significant economic activity in its own right,with the potential for the UK to be a global leader in a new multi-billion pound industry.”See The roadmap to an effective AI assurance ecosystem,Centre for Data Ethics and Innovation,2021.77 Pro-innovation Regulation of Technologies Review:Digital Technologies,HM Treasury,2023.20A pro-innovation approach to AI regulation