转型 AI 工作通常需要以下能力：
101.Government has prioritised the ongoing assessment of the different capability needs across the regulatory landscape.We will keep this under close review as part of our ongoing monitoring and evaluation activity.102.While our approach does not currently involve or anticipate extending any regulator’s remit,150 regulating AI uses effectively will require many of our regulators to acquire new skills and expertise.Our research151 has highlighted different levels of capability among regulators when it comes to understanding AI and addressing its unique characteristics.Our engagement has also elicited a wide range of views on the capabilities regulators require to address AI risks and on the best way for regulators to acquire these.103.We identified potential capability gaps among many,but not all,regulators,primarily in relation to:AI expertise.Particularly:o Technical expertise in AI technology.152 For example,on how AI is being used to deliver products and services and on the development,use and applicability of technical standards.153o Expertise on how AI use cases interact across multiple regulatory regimes.o Market intelligence on how AI technologies are being used to disrupt existing business models,both in terms of the potential opportunities and risks that can impact regulatory objectives.Organisational capacity.A regulator’s ability to:o Effectively adapt to the emergence of AI use cases and applications,and assimilate and share this knowledge throughout the organisation.o Work with organisations that provide assurance techniques(e.g.assurance service providers)and develop technical standards(i.e.standards development organisations),to identify relevant tools and embed them into the regulatory framework and best practice.o Work across regulators to share knowledge and cooperate in the regulation of AI use cases that interact across multiple regulatory regimes.
感谢你耐心阅读这篇略显冗长的文章。让我们简单回顾一下，首先，我们讨论了什么是AI工作流。简单来说，就是把AI工具融入到工作里的各个环节中，为我们的工作来提效。然后，我们聊到了搭建AI工作流需要的三层能力：第一层，了解各种AI工具，知道每个AI工具的特点和用途。第二层，学会写提示词，这是很关键，决定你能不能把任务给AI说清楚。第三层，搭建AI智能体，让替代人工，使用多个AI工具协同工作，自动完成任务。接下来，我让AI帮我梳理出了这套搭建AI工作流和公众号工作流的SOP：
1.19.AI is already delivering major advances and efficiencies in many areas.AI quietly automates aspects of our everyday activities,from systems that monitor traffic to make our commutes smoother,17 to those that detect fraud in our bank accounts.18 AI has revolutionised large-scale safety-critical practices in industry,like controlling the process of nuclear fusion.19 And it has also been used to accelerate scientific advancements,such as the discovery of new medicine20 or the technologies we need to tackle climate change.212.20.But this is just the beginning.AI can be used in a huge variety of settings and has the extraordinary potential to transform our society and economy.22 It could have as much impact as electricity or the internet,and has been identified as one of five critical technologies in the UK Science and Technology Framework.23 As AI becomes more powerful,and as innovators explore new ways to use it,we will see more applications of AI emerge.As a result,AI has a huge potential to drive growth24 and create jobs.25 It will support people to carry out their existing jobs,by helping to improve workforce efficiency and workplace safety.26 To remain world leaders in AI,attract global talent and create high-skilled jobs in the UK,we must create a regulatory environment where such innovation can thrive.3.21.Technological advances like large language models(LLMs)are an indication of the transformative developments yet to come.27 LLMs provide substantial opportunities to transform the economy and society.For example,LLMs can automate the process of writing code and17 Transport apps like Google Maps,and CityMapper,use AI.18 Artificial Intelligence in Banking Industry:A Review on Fraud Detection,Credit Management,and Document Processing,ResearchBerg Review of Science and Technology,2018.19 Accelerating fusion science through learned plasma control,Deepmind,2022;Magnetic control of tokamak plasmas through deep reinforcement learning,Degrave et al.,2022.