AI and Digital in 2023: From a winter of excitement to an autumn of clarity

Main developments in generative AI

Source: https://www.globalxetfs.com/

Main developments that reached the headlines:

In addition to ChatGPT, several other notable generative AI models, such as Midjourney, Meta’s open-source Llama models, Baidu’s AI Ernie Bot and Google’s Bard and Gemini, have been released or updated.

Elon Musk and over 1,000 other technology leaders and researchers have called for a pause on the development of the most advanced AI systems, citing ‘profound risks to society and humanity’. In an open letter, they urged AI developers to pause training AI systems more powerful than GPT-4 for at least six months, initiating a broader debate about the potential risks of technology, with some even calling AI a threat to humanity.

In 2023 OpenAI, Stability AI, and Anthropic have been sued by writers and developers for copyright infringement. They claim these tools are built on massive data sets using their copyrighted content without their consent or compensation. 

ChatGPT was briefly banned in Italy due to privacy concerns. Italy’s data protection watchdog accused OpenAI, the company behind ChatGPT, of unlawfully collecting personal data from users and not having an age-verification system in place. The company complied with watchdog requests, but it raised concerns about privacy.

OpenAI upgraded ChatGPT with web browsing capabilities. With the ability to browse the web, ChatGPT can now provide the latest information available on the internet, access a wider range of information, authoritative sources, and links to images and videos, and deliver more accurate and relevant responses to user queries.

The Sam Altman saga at OpenAI has been a rollercoaster ride, with Altman’s fate being a topic on everyone’s lips. On 17 November 2023, OpenAI’s board of directors dismissed Altman from his CEO position. However, this move triggered a strong response from OpenAI’s employees, who rebelled against the board’s decision. They threatened to defect to Microsoft to join Altman and co-founder Greg Brockman if they were not reinstated. It all culminated in an announcement on 21 November 2023, with Altman’s reinstatement as CEO.

AI governance – The global landscape of AI governance is gradually taking shape.

The United States: On 30 October, President Biden issued an executive order mandating AI developers to provide the federal government with an evaluation of the data of their applications used to train and test AI, its performance measurements, and its vulnerability to cyberattacks. Read more in our Newsletter. 

EU lawmakers reach a deal on AI Act: The EU has reached a provisional agreement on the AI Act. The draft legislation still needs to go through a few steps for final endorsement, but the political agreement means its key elements have been approved – at least in theory. There’s quite a lot of technical work ahead, and the act does have to go through the EU Council, where any unsatisfied countries could still throw a wrench into the works. The act will go into force two years after its adoption, which will likely be in 2026. Read more in our Newsletter. 

China: China was the first country to introduce its interim measures on generative AI, effective in August this year. What is the aim? To solidify China’s role as a key player in shaping global standards for AI regulation. China also unveiled its Global AI Governance Initiative during the Third Belt and Road Forum, marking a significant stride in shaping the trajectory of AI on a global scale. China’s GAIGI is expected to bring together 155 countries participating in the Belt and Road Initiative, establishing one of the largest global AI governance forums. Read more in our Newsletter.

The UN Security Council on AI: The UN Security Council held its first-ever debate on AI, delving into the technology’s opportunities and risks for global peace and security. In his briefing to the 15-member council, UN Secretary-General Antonio Guterres promoted a risk-based approach to regulating AI and backed calls for a new UN entity on AI, akin to models such as the International Atomic Energy Agency, the International Civil Aviation Organization, and the Intergovernmental Panel on Climate Change. Read more in our Newsletter and AI-generated summary of country positions, prepared by DiploGPT.

G7: The G7 nations released their guiding principles for advanced AI, accompanied by a detailed code of conduct for organisations developing AI. A notable similarity with the EU’s AI Act is the risk-based approach, placing responsibility on AI developers to assess and manage the risks associated with their systems. Read more in our Newsletter. 

UK AI Safety Summit: The UK’s summit resulted in a landmark commitment among leading AI countries and companies to test frontier AI models before public release. The Bletchley Declaration identifies the dangers of current AI, including bias, threats to privacy, and deceptive content generation. While addressing these immediate concerns, the focus shifted to frontier AI—advanced models that exceed current capabilities—and their potential for serious harm. Read more in our Newsletter. 

The UN’s High-Level Advisory Body on AI: The UN has launched a High-Level Advisory Body on AI comprising 39 members. Led by UN Tech Envoy Amandeep Singh Gill, the body published its first recommendations in December (Interim Report: Governing AI for Humanity), with final recommendations expected next year. These recommendations will be discussed during the UN’s Summit of the Future in September 2024.

The UN GA Resolution on Lethal Autonomous Weapons Systems or LAWS: On 22 December, the UN General Assembly adopted a resolution aimed at advancing international regulations concerning weapons utilising AI (in war) or Lethal Autonomous Weapons Systems (LAWS). This resolution seeks to address the development of weaponry capable of autonomously selecting human targets without human intervention.

Chips and geopolitics

Chips are the primary geopolitical battleground between China and the United States, with two key dynamics. The first is trade and restricting the export of chips and manufacturing equipment to China, particularly from the United States and its allies. Second, national capacity development for semiconductor design and manufacturing is being accelerated.

The most significant surprise occurred in 2023 when Huawei released the Mate 60 Pro phone. This phone is equipped with an advanced Kirin 9000S chip that is based on 7 nanometers technology, which was not something that was anticipated to be available in China. It is not entirely clear whether the sanctions regime that the United States has imposed on the technology of semiconductors is ineffective or whether China has independently developed new technologies for advanced semiconductors.

In this contest, the Netherlands has the most advanced semiconductors technology, including deep ultraviolet (DUV) lithography systems for the development of advanced microchips. China initiated a trade dispute procedure at the World Trade Organization (WTO) against US chip export control measures, arguing that these measures ‘threatened the stability of the global industry supply chains’.

Many countries are developing their national semiconductor capacities. Japan aims to treble sales of domestically made microchips by 2030. The EU set into motion a comprehensive microchip strategy around the EU Chips Act, which entered into force on 21 September 2023.

The USA and Canada have pledged more money for domestic semiconductor companies: The USA pledged US$50 million for the Defense Production Act that will fund advancing packaging for semiconductors and printed circuit boards, while Canada pledged up to CA$250 million for semiconductor projects from the Strategic Innovation Fund. 

As North American countries make another move to reduce their reliance on Asian chipmakers, two other countries took steps in the opposite direction. A delegation of Czech politicians and company representatives hopes for Taiwanese investment in Czech chip technologies. Brazil will reportedly seek mainland Chinese technology and investment in developing its semiconductor industry. 

China has undertaken ambitious initiatives – the ‘new whole-nation system.’ This program aims to bolster its semiconductor sector by leveraging state resources, diverting investments, and prioritising the development of cutting-edge technologies. Essentially the aim is to achieve self-reliance on advanced technology. As a response to the imposed US restrictions from October 2023, China’s trade council has urged a reconsideration of rules limiting American investments in the country’s tech sector. The council contends that these restrictions lack clarity in distinguishing between military and civilian applications. The council argues that the restrictions are vague and do not differentiate between military and civilian applications Simultaneously, Chinese tech firms like Baidu are diversifying their supply chains, seeking alternatives to reduce reliance on US-based semiconductor providers.

Geopolitics of submarine cables

Submarine cables became the focus of global interest following the Nord Stream blast. Cutting major submarine cables could create havoc in our digitally interdependent civilisation.  In the same context, Prof. Jeffrey Sachs sent a warning message at the UN Security Council hearing on the risks for digital cables. NATO has also set up a Critical Undersea Infrastructure Protection Cell with one of the main aims to protect internet submarine cables.

Another area of increasing decoupling between China and the US is submarine cables. The US has declined landing rights for a few new submarine cables that have Chinese landing points or involve Chinese companies in cable laying or management. Following Chinese retaliation, it is very likely that two parallel submarine cable systems led by China and the United States will emerge.

Geopolitics of outer space

In January, we said that outer space activities would likely get more attention in governance and diplomacy talks. And, indeed, quite a lot has been going on over the past 12 months. At the UN level, the Open-ended Working Group on reducing space threats (OEWG-Space) through norms, rules, and principles of responsible behaviour held its third session and saw member states discuss a wide range of issues, from preventing harmful interferences in space, to addressing threats against space objects (in particular satellites), and preventing an arms race in outer space.

At the UN Office for Outer Space Affairs, two new working groups were created to explore: (a) the status and application of the five UN treaties on outer space, and (b) the legal aspects of space resource activities. Meanwhile, space agencies and private actors are coming up with new initiatives and plans. Just a few examples: competition is picking up in low-earth orbit communication networks, as China’s Aerospace Science and Technology Corporation and Amazon’s project Kuiper are preparing to launch satellite constellations to compete with the services provided by the likes of Starlink and OneWeb. With the moon back in the focus of space exploration activities, plans are unfolding—within the European Space Agency (ESA) and US company Lockheed Martin, for instance—to deploy new communication networks around our earth’s natural satellite. 

What did we predict for space geopolitics in January 2023?

Satellites may offer some alternatives, but they can’t replace fibre as a global backbone. They have also been shown to be susceptible to geopolitics, such as the hacking of ViaSat or Musk’s pondering whether to continue the provision of Starlink services to Ukraine. Beyond the role that satellites play in giving people access to the internet or letting them talk to each other in an emergency, outer space activities are likely to get more and more attention in governance and diplomacy talks in the coming years. Issues related to frequency interferences, satellite collisions, the cyber-resilience and security of space services, space debris, the exploration of space resources, and the growing competition between states as well as between private actors will continue to grow in relevance, building on recent developments. 

In 2022 we saw, for instance, a new ITU resolution calling for strengthened public-private cooperation in ensuring that ‘the benefits of space will be brought to everyone, everywhere’; the launch of a UN Open-ended working group on reducing space threats through norms, rules, and principles of responsible behaviours; and a growing number of countries joining the Artemis Accords (spearheaded by the USA, the Accords outline principles to enhance the governance of civil exploration and use of outer space). It is also telling that the 2024 Summit of the Future, called for by the UN Secretary-General, is expected to include a track on outer space, with the goal to ‘seek agreement on the sustainable and peaceful use of outer space’.

Dive deeper: Space diplomacy  

Metaverse in 2023

Apart from AI, last year was technologically quiet. Metaverse technologies have lost momentum as a part of the overall tech sector crisis. Tencent Holdings abandoned its plans to enter the virtual reality hardware market, while Microsoft announced that it is closing its enterprise metaverse division. In a letter to his staff, Mark Zuckerberg signalled reduced support for the Metaverse as their ‘single largest investment is in advancing AI and building it into every one of our products’.

It is noteworthy that the development of the metaverse has garnered greater attention from Asian governments in comparison to the rest of the world, particularly in China and South Korea. These countries are exploring the potential of metaverse technology beyond gaming, with applications in industry and public administration. South Korea’s Ministry of Science and ICT has a Metaverse Fund to drive metaverse initiatives in the country, and Seoul officially launched its metaverse platform. Meanwhile in China, Shanghai, and Zhejiang have implemented metaverse development strategies in 2022.

Apple, in mid-2023, launched its Vision Pro mixed-reality headset that seamlessly blends digital content with the physical world. The headset is designed to cater to both virtual and augmented reality experiences, and it allows users to switch between AR and VR. Meta’s Ray-Ban smart glasses gained the most media attention. These smart glasses are a next-generation wearable tech device that integrate AI technology, making them more intelligent than previous models and introducing many new features. 

The first ITU Forum on embracing the metaverse took place on ​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​7 March 2023 in​ Riyadh, Saudi Arabia and begin ITU’s endeavour to promote metaverse pre-standardisation initiatives. The forum’s objective is to facilitate global dialogue on the metaverse, provide inputs, and discuss relevant topics that can aid the work of the newly established ITU Focus Group on the metaverse.

The ITU Focus Group on metaverse which was established in late 2022 held its first meeting in March 2023. This group aims to develop a roadmap for setting technical standards to make metaverse services and applications interoperable, enable a high-quality user experience, ensure security, and protect personal data.

The European Commission has adopted a strategy for Web 4.0 and virtual worlds. The EU strategy aims to steer the next technological transition and ensure an open, secure, trustworthy, fair, and inclusive digital environment. The strategy aims to empower people and reinforce skills, support a European Web 4.0 industrial ecosystem, promote virtual public services, and shape global standards for open and interoperable virtual worlds. The Commission believes that Web 4.0 will be the next generation of internet infrastructure which will allow integration between digital and real objects and environments

China’s Ministry of Industry and Information Technology (MIIT) revealed plans to create a working group dedicated to defining standards for the metaverse. This initiative aims to expedite the process of standardizing the concept of the metaverse. MIIT emphasized the importance of keeping pace with global advancements in this field to maintain alignment with international developments.

The US Federal Communications Commission (FCC) has given the green light to a new class of very low-power devices, including augmented reality (AR) and virtual reality (VR) headsets, to utilise the 6 GHz. This development is expected to have a tangible impact on the technology market by enabling faster data transfers and minimizing interference. For several years, major tech companies, including Apple, Google, Microsoft, and Meta, have been advocating for access to the 6GHz band. 

Blockchain in 2023

Blockchain technology was used in 2023 mostly as an underlying structure of the digital identity networks (digital ID) which were launched extensively throughout 2023. 

Apart from government approved solutions, the digital identity network Worldcoin created by the OpenAI CEO Sam Altman caught most of the world’s attention. Several countries worldwide expressed concerns regarding the Worldcoin project and issues surrounding the privacy of the biometric data collected for the purpose of authentication.

New forms of open blockchains were tested by the finance industry in an effort to make payments more transparent and trustworthy for everyone online. Open permissionless blockchain Solana was used in a pilot case by Visa. Solana is a second class of permissionless blockchains which enables a scaling solution to achieve massive transactions. Digital Collectibles or Non-fungible Tokens (NFTs) were less in the focus in 2023. In fact, regulators’ scrutiny didn’t miss this new market. Some famous celebrities and public figures were indicted for promotion of NFTs. US regulators saw this behaviour as an unregistered offering of crypto asset securities.

With the G20 summit endorsing India’s DPI framework and its plan for a global repository for DPI products, digital public infrastructure went from being a niche term just a year or two ago to a globally recognised driver of economic development.

This historic recognition and creation of a global repository for digital public infrastructure was closely followed by the creation of a Social Impact Fund to advance DPI in the Global South, and the One Future Alliance (OFA). India now supports the development of digital public infrastructure in Low- and Middle-income Countries (LMICs), through numerous initiatives noted in the the Bengaluru declaration of G20 Digital Ministers. 

India further accelerated IBSA digital momentum when it offered developing countries such as the Philippines, Morocco, Ethiopia, and Sri Lanka the Modular Open Source Identity Platform (MOSIP), an export version of Indian identity system Aadhar. The DPI sharing consists of a triad of identity, payment, and data management applications.

IBSA countries will remain relevant as Brazil assumed the presidency in March, celebrating the 20th anniversary of the dialogue forum, and is set to take the presidency of the G20 Forum in 2024. 

GDC saw several milestones this year. Rwanda and Sweden, as co-facilitators, announced the roadmap for the GDC process in January which was further updated in May, and we also saw other regions shaping up their positions.

The process saw two main documents delivered this year. In May, the UN Secretary-General issued a policy brief for the GDC, outlining eight areas in which ‘the need for multistakeholder digital cooperation is urgent’ and could help advance digital cooperation: digital connectivity and capacity-building; digital cooperation to accelerate progress on the SDGs; upholding human rights; an inclusive, open, secure and shared internet; digital trust and security; data protection and empowerment; and agile governance of AI and other emerging technologies.

The most notable proposal is to establish the annual Digital Cooperation Forum to be convened by the Secretary-General. It is expected to facilitate collaboration across digital multistakeholder frameworks and reduce duplication, promote cross-border learning in digital governance, and identify policy solutions for emerging digital challenges and governance gaps.  The brief also suggested establishing a trust fund to sponsor a Digital Cooperation Fellowship Programme to enhance multistakeholder participation.

In September co-facilitators Rwanda and Sweden released an Issues Paper outlining their assessment of the deep dives and consultations conducted in relation to the GDC. 

The GDC is moving from multistakeholder consultation to multilateral negotiations. The policy brief proposed several mechanisms.

We also witnessed the energising effect of the GDC process on different communities, encouraging stakeholder involvement at the IGF 2023 during the main Session on GDC: A Multistakeholder Perspective and garnering support at the UNGA78.

Framed by the outcomes of the 2023 IGF, the GDC is to be agreed upon in the context of the Summit of the Future in 2024 and is expected to ‘outline shared principles for an open, free and secure digital future for all’. For the upcoming year, permanent representatives of Sweden and Zambia to the UN were appointed as co-facilitators of the GDC process. 

In 2023, the protection of privacy and personal data in the digital space was at the centre of multiple digital policy developments around the world. We have already mentioned above the (relatively) new concerns about the implications of generative AI for privacy and data protection – something that more and more privacy watchdogs are looking into. Besides this, there have been several regulatory, enforcement, and self-regulatory developments worldwide, from India’s and Saudi Arabia’s initiatives to strengthen the legal protections for personal data, through Ireland fining Meta €5.5 million for data breaches, to Google banning personal loan apps from accessing sensitive data. On other fronts, the EU and Japan have concluded the first review of their Mutual Adequacy Arrangement on personal data protection, and the UN Special Rapporteur on privacy has called on governments to delete personal data collected during the COVID-19 pandemic.

International Women’s Day in early March brought important attention to gender rights. Some of the highlights included debates on the (potential) role of AI in achieving gender equality, the launch of UNESCO’s Women 4 Ethical AI platform, calls to accelerate progress towards bridging digital gender gaps and to meaningfully consider gender issues in the development of the Global Digital Compact, and the release of a new report on the digital targeting of LGBT people. 

Privacy and inclusion—the two issues we have explored above—were also highlighted in the Ibero-American Charter of Principles and Rights in Digital Environments, adopted by the Organization of Ibero-American States. The charter outlines ten principles to guide meaningful digital inclusion, from privacy and security, to fairness and inclusiveness. Another multilateral initiative that saw the light of day recently is the Guiding Principles on Government Use of Surveillance Technologies, a non-binding instrument developed by the 36 member states of the Freedom Online Coalition.

The year 2023 was a critical one for online content moderation. Major tech companies, including Alphabet, Meta, and X, faced significant challenges due to layoffs, content moderation policy reversals, and new legislation coming into force. 

Experts warned that the reversal of content policies at Alphabet, Meta, and X threatened democracy. Media watchdogs highlighted that the layoffs at these top social media firms created a ‘toxic environment’ as the 2024 elections await next year. The layoffs, numbering more than 40,000, were seen as a threat to the health and safety of these platforms. X (formerly Twitter) got onto the EU Commission’s radar for having significantly fewer content moderators than its rivals.

The European Union (EU) led the way in drafting internet and social media laws, including regulations around content moderation. The Digital Services Act (DSA), approved by the Council of the EU in July 2022, enabled Ireland to hold the online platforms accountable for their content. These regulations included the immediate takedown of illegal content, mandatory risk assessments of algorithms, and increased transparency in content moderation practices.

In August, the DSA began implementing strict online content measures on 19 very large online platforms and search engines. These measures ranged from the obligation to label all adverts and inform users who’s behind the ads, to allowing users to turn off personalised content recommendations. The DSA’s impact extended beyond the boundaries of the EU, affecting any company servicing European users, regardless of where it is based.

Major social media platforms were additionally warned about non-compliance in digital diplomacy when Thierry Breton flew to Silicon Valley in August to remind Big Tech CEOs about Brussels’ expectations. Previously, X, for instance, pulled out of the code to tackle disinformation, but Breton insisted on its compliance with the DSA when operating in the EU.

Besides Twitter turning into X, TikTok developments marked this year. In the US, several states introduced legislation to ban the app. Critics argued that banning TikTok may violate First Amendment rights and would set a dangerous precedent of curtailing the right to free expression online. 

TikTok, seen as an extended arm of the Chinese government, faced broader backlash as Belgium, Norway, the Netherlands, the UK, France, New Zealand, Austria, and Australia issued guidelines against installing and using TikTok on government devices. In response, China ‘made solemn démarches’ to Australia over the Australian ban on TikTok on government devices. 

Content moderation also hit a rather massive bump in late 2023 with the onset of global conflicts when the platforms drew a lot of criticism for failing to combat harmful content. As people grappled with the violence unfolding in Israel and Gaza, social media platforms became inundated with graphic images and videos of the conflict. This made it hard for anyone looking for information about the conflict to parse falsehood from truth. 

In response to these challenges, tech companies took various measures. Meta established a special operations centre staffed with experts, including fluent Hebrew and Arabic speakers. TikTok established a command centre for its safety team, added moderators proficient in Arabic and Hebrew, and enhanced automated detection systems. X removed hundreds of Hamas-linked accounts and removed or flagged thousands of pieces of content.

Content moderation saw its day, or should we say days, in court as well. Meta, the parent company of Facebook and Instagram, confronted a legal battle initiated by over 30 US states. The lawsuit claimed that Meta intentionally and knowingly used addictive features while concealing the potential risks of social media use. And in the UK, the Online Safety Act came into effect, imposing new responsibilities on social media companies.

In an interesting development in global digital policy, UNESCO has been working on a set of Guidelines for regulating digital platforms – an international and soft law approach to content policy.

Finally, the ease of content generation with AI has marked a significant risk to the digital information space and especially the upcoming elections, contributing to the spread of fake news, deepfakes, and overall challenging the democratic electoral process. We also saw Meta outline a new policy on AI political advertising.

In 2023, we’ve seen a rise in cyberattacks across the board. Cyber operations aimed at nations were plentiful this year. Some examples include cyberattacks on the government websites of Colombia, Italy, Sweden, Senegal, and Switzerland. A ransomware attack on Sri Lanka’s government cloud system resulted in data loss for 5,000 affected accounts. 

Critical infrastructure was also targeted: for instance, Martinique faced weeks of disruptions due to a cyberattack that affected its internet connectivity and critical infrastructure. The Five Eyes cyber agencies attributed cyberattacks on US critical infrastructure to the Chinese state-sponsored hacking group Volt Typhon, which China has denied. 

Cyber espionage groups were also busy: the USA and South Korea issued a joint advisory warning that North Korea uses social engineering tactics in cyberattacks. A trove of leaked documents, dubbed the Vulkan files, have revealed Russia’s cyberwarfare tactics against adversaries such as Ukraine, the USA, the UK, and New Zealand. The heads of security agencies from the USA, the UK, Australia, Canada, and New Zealand, collectively known as the Five Eyes, have publicly cautioned about China’s widespread espionage campaign to steal commercial secrets.

On the cybercrime front, many organisations were struck by cyberattacks this year, too many to enumerate here. Ransomware has reached record levels due to the exploits of the MOVEit software. This hack and the attack on 3CX have again highlighted that supply chain security is a significant concern for industries and the public sector.

We’ve also seen claims that threat actors use AI in cyberwarfare and cybercrime to spread disinformation online, craft sophisticated fake images and videos for phishing campaigns, and create malware.

Cyber threats are transnational by nature, and so nations have banded together to tackle them. There have been some wins for the ‘good guys‘ in fighting cyber threats. For example, joint operations disrupted the Russia-linked Hive ransomware network and the Qakbot malware botnet. International law enforcement agencies also seized the dark web’s Genesis Market, which was popular for selling digital products to malicious actors. Multilateral efforts are also underway, such as the CRI, the UN OEWG (which deals with the responsible behaviour of states in cyberspace) and the Ad Hoc Committee on Cybercrime (which is mandated to draft a resolution on cybercrime). 

In 2023, the OEWG has reached the mid-point of its mandate. The group held its fifth and sixth substantive sessions in 2023, and it is making headway on capacity development and confidence-building measures (CBMs). Cyber capacity building is seen as crucial in enabling countries to identify and address cyber threats while adhering to international law and norms for responsible behaviour in cyberspace.

Countries have therefore been able to determine some of the next steps, including a) a mapping exercise planned for March 2024 that aims to survey global cybersecurity capacity building initiatives comprehensively and b) a roundtable scheduled for May 2024 showcasing ongoing initiatives, creating partnerships, and facilitating a dynamic exchange of needs and solutions. There’s widespread support for establishing the global Points of Contact (PoC) directory as a valuable CBM, so much so that countries will be invited to nominate PoCs at the beginning of 2024. Dedicated meetings on the PoC are also planned, including an informal online information session on the directory in February and an intersessional meeting to discuss stakeholders’ role in the PoC directory in May.

With the concluding session of the Ad Hoc Committee on Cybercrime (AHC) approaching in January 2024, establishing an international convention on cybercrime seems so close, yet contentious issues remain. The main question from 2022 is: did the AHC achieve a draft text of the convention in 2023? Yes, after three sessions in January, April, and August of 2023, there is a draft text of the convention, with the latest revised in November 2023. 

However, as international human rights organisations, including Article 19,  have warned, if offences expand to any crimes, it could result in repressive tools and authoritarian governments. This is mainly because the offences considered under the preamble of the draft text of the convention are not limited to cyber-dependent crimes which rely on cyber elements for their execution. 

Another issue relates to the cross-border cooperation between states stipulated under Article 40 of the draft text of the convention, which allows the exchange of information about individuals who have committed a criminal offence under the convention. This lack of data protection measures raises the possibility of introducing additional surveillance powers, potentially conflicting with international legal obligations, especially for states party to the Budapest Convention (Convention on Cybercrime), currently the only internationally binding legal instrument on cybercrime. Therefore, conflicts with existing international instruments would be inevitable if laws are not harmonised.

ITU’s 2023 report ‘Facts and Figures’ recognised that connectivity continued to be more affordable in all regions of the world and for all income groups. However, the report stated that ‘lack of affordability continues to be a key barrier to Internet access particularly in low-income economies. A wide gap persists between high-income economies and the rest of the world’
This was one of the main topics of the 2023 UNCTAD’s eWeek, as some of the biggest world economies such as India, China, and the European Union pledged additional resources to improve the benchmark of their digital economies. 

Bilateral agreements around the development of the digital economy have become more common. Japan and the EU strengthened ties in the third High-Level Economic Dialogue, while the US and UK announced the Atlantic Declaration for a Twenty-First Century, with a focus on the digital economy.

Worldwide spending on digital transformation technologies and services continued to grow at the expected rate.

What did we predict for the digital economy in January 2023?

The digital economy will face the full brunt of the economic crisis, with a possible recession in 2023. There will be less money for the next big thing – whatever it may be. As investors opt for safe economic options, digital investments are unlikely to be their table of choice.

Bitcoin, often labelled as the new gold, has lost its allure due to the recent failures of cryptocurrencies. Web 3.0 dynamism has slowed down. Quantum computing is too far away on the horizon to make a major economic impact. 

In digital economy governance, the main focus will be on digital trade, data flows, the implementation of the new global tax deal, and the regulation of cryptocurrencies.

---

As the economic crisis unfolds worldwide, the digital economy will face the full brunt. Things aren’t looking up for the ‘next big thing’ – there’s not much money around.

With so many daunting prospects for the economy, the governance of the digital economy will focus on three main areas: free trade, data flows, and the implementation of the new global tax deal.

Cryptocurrencies

The beginning of 2023 brought some of the hardest challenges for the cryptocurrency industry. After the December arrest of Sam Bankman-Fried we predicted a harder regulatory push toward the crypto industry. In February, the US cryptocurrency company Paxos was ordered by the New York Department of financial services (NYDFS) to stop the issuance of the BUSD stablecoin. The BUSD stablecoin was a significant money line for online exchanges as it served as a bridge from the crypto industry to the traditional banking and investment arena.

This stablecoin was closely connected to the world’s biggest crypto exchange Binance, which was again in the focus of US regulators in April when the US Commodity Futures Trading Commission (CFTC) filed a suit against them. The Binance exchange and the company CEO Changpeng Zhao are accused of trading violations. Stablecoin regulation was on the agenda of the G20 Finance Ministers meeting on February 24-25 in India.

They also discussed what we thought would be the focus for 2023, the design and issuing of the Central Bank Digital Currency [CBDC]. The EU is finalising its plans, while the BIS is working with other central banks for the final push. 

After the collapse of Silicon Valley Bank, which was a bank of choice for a large part of the US crypto industry, a colder climate was also announced by the Biden administration. The new 2024 Revenue Proposal in the US will consider progressively taxing electricity that is used for cryptocurrency mining. We also predict a sharper focus on the requirements and measures for an environmentally responsible industry.  

The European Parliament has approved the Markets in crypto-assets (MiCA) regulation, and comprehensive legislation for the crypto and digital assets industry. Central Bank Digital Currencies (CBDC) continued to be on the central bank’s agenda. The BIS report shows that the financial sector is ready for this innovative technology, while the European Central Bank has announced a two-year preparation phase for the launch of the digital euro.

Cryptocurrency regulation was also in the focus of the G20 group throughout 2023. The G20 group released a joint paper with the IMF, outlining policy and regulatory recommendations to address cryptocurrency regulation. According to a Chainalysis, a crypto research firm, the global adoption of cryptocurrencies is predominantly being led by lower-middle-income countries.

What did we predict for cryptocurrencies in January 2023?

A time of reckoning for cryptocurrency

The year 2022 delivered two opposite sides of the cryptocurrency hype cycle. After all-time high values in late 2021, the year 2022 started with a declining trend which proved to be constant throughout the year. 

Currently, bitcoin sits at US$16,500, which is an issue for bitcoin miners, as this price is on the edge of the costs of mining. This led one of the largest publicly traded cryptocurrency firms Core Scientific (USA) to file for bankruptcy in December 2022. 

_{Bitcoin price fluctuations over the span of a year.}

The year 2022 will be remembered as a year of major breakdowns for the industry’s big players. It started with the collapse of ‘algorithmic stablecoins’ like Luna, extended to the cryptocurrency landing platforms like Celsius, and finished with a bang: the fall of the third largest cryptocurrency exchange in the world, FTX.

The FTX exchange, headquartered in the Bahamas, misused more than US$2.5 billion of their customers’ funds, syphoning it to a sister company Alameda Research. This high-profile case raised the concerns of regulators worldwide. In 2023, states will continue to adopt digital asset regulations, in particular related to consumer protection, and the clear involvement of the financial institutions in control of the industry. 

It will certainly be a year of reckoning. The key question will be the one which The Economist posed: Can crypto survive its latest winter?

Digital trade 

The World Trade Organization (WTO) increased efforts to negotiate on e-commerce in 2023 in spite of set-back of the US withdrawal from negotiations.

In 2019, a subset of WTO members came together to form the Joint Statement Initiative (JSI) on e-commerce. The group of 87 member states are working towards a binding agreement, covering both classical trade topics, such as market access and trade facilitation, as well as digital policy issues, such as data flows and localisation, online privacy, cybersecurity, and spam. Many developing countries, including India and South Africa, are critical of this process. But since the parties negotiating to make up 90% of global trade, any deal made within this framework will have big effects on how e-commerce is regulated around the world.  

During the past few years, JSI negotiators have managed to agree on some topics that could be considered ‘low hanging fruit’, including spam, electronic signatures and authentication, open government data, consumer protection, and transparency.

During the second half of 2022, the JSI co-convenors—Australia, Japan, and Singapore—launched a stocktaking effort to identify proposals that did not attract enough support, encouraging proponents to withdraw them. A new consolidated version of the negotiating text shows that progress still needs to be made in bridging positions on the most controversial issues, such as data flows, data localisation, and privacy. This new version is the basis for 2023 negotiations. 

JSI members have a difficult task ahead if they want to produce a new agreement by the end of the year. An alternative option would be to aim for a ‘tiered outcome’, securing a more modest agreement on issues that promote more convergence among participants while continuing negotiations on other issues in 2024 – a solution that will upset those countries that have placed emphasis on the most digital topics in the negotiating agenda, and which perceive these issues as the key to a truly meaningful outcome.

The importance of mainstreaming development aspects of e-commerce is also clear. However, development aspects could remain insufficiently tackled if they are only covered by horizontal and general provisions. Deeper vertical commitments made under specific topics could be a viable option.

While negotiations are still on hold at the WTO, digital trade continues to be regulated by free trade agreements and digital economy agreements, which are mushrooming across the world. The JSI has been seen not only as a breath of fresh air at the WTO, potentially bringing new dynamism to negotiations, but also as a way to counter a growing fragmentation on the digital trade norm landscape.

The Association of Southeast Asian Nations (ASEAN) has initiated talks about a Digital Economy Framework Agreement (DEFA) to create and implement digital public infrastructure within its ten-member bloc. Global exports of digitally delivered services continued to grow, with the EU and East Asia leading the charts. Africa and LDCs continued to lag behind, with Africa holding less than 1% share of world exports of digital goods

The European Commission has designated six tech companies, Alphabet, Amazon, Apple, ByteDance, Meta, and Microsoft, as gatekeepers under the Digital Markets Act

While some companies accepted a new role designated by the European Union, others are still trying to mitigate the responsibilities.  

Implementing the new global tax deal

Celebrated as one of the major deals brokered by the Organisation for Economic Co-operation and Development (OECD), the global tax deal faces a tough test: how to implement it. 

The tax deal, also known as the two-pillar solution (with Pillar I focusing on the reallocation of profits to those countries where there is actual activity, and Pillar II setting a global minimum tax of 15%), has been backed by over 130 countries. 

The negotiations on Pillar II are the most advanced. Countries around the world have been publishing draft proposals and launching national public consultations. In December 2022, the EU finally agreed on a draft directive to implement Pillar II in the EU bloc. This came after almost a year of negotiations, first blocked by Poland, and then blocked by Hungary for six months. The USA has also passed a 15% minimum tax (the Inflation Reduction Act), however it still needs to be refined (or reconciled) with the OECD’s global minimum tax to be fully compliant with Pillar II. So what to expect in 2023? 

These negotiations will continue. The USA has work to do. So does the EU, albeit the major impasse seems to be over now. The ultimate aim is that all countries who agreed to the OECD global tax deal in 2021 will eventually have their legislation in order. With the exception of the handful of countries in the no-camp, corporations will not be able to seek refuge in any tax havens, as most countries will have a minimum of 15% tax rate.

However, since the pillars are tied together, we can also expect that some countries will not want to go all the way on Pillar II before there is enough groundwork on how to implement Pillar I.

The negotiations on Pillar I are also moving forward. One of the main challenges is that the technical discussions are complex and lengthy. Pillar I will also require countries to drop their unilateral taxes. But if the process takes too long, especially on the USA side (USA companies will be hit the most by the new global tax rule), countries such as Canada will continue threatening to impose new unilateral taxes, or keep existing ones in place. So what can we expect here?

In 2023, complex negotiations will continue to design Pillar I’s ‘Amount A’ (the new taxing right for jurisdictions over parts of the profits made by multinational companies) and ‘Amount B’ (how to price a company’s baseline marketing and distribution activities). The multilateral convention originally planned to be finalised by mid-2022, is now expected by mid-2023. When it comes to the more advanced Pillar II, the multilateral instrument that will implement parts of the new rules is now also expected to be finalised by mid-2023. 

Meanwhile, the biggest risk is stalled negotiations related to Pillar I, which could jeopardise the implementation of Pillar II. Countries could also continue to propose new unilateral tax rules in the hope that this will speed up Pillar I negotiations. Whatever unilateral rules are proposed, these will have to be temporary until the global OECD rules are implemented.  

There is also an ongoing debate on the impact on developing countries. All of these rules, developing countries say, will favour mostly developed countries, so, there needs to be more incentive for developing countries to implement them. In addition, the rules are too complex. What can we expect here? Major players in the global tax deal debate are the USA and the EU. Developing countries may continue to raise concerns, but they do not have enough leverage to change the rules. Regarding complexity, we can also expect the OECD to try to simplify the implementation of the rules, as it started doing in 2022. It’s a tall order, however—tax rules are inherently complex.  

Responding to the call for a pause in ‘giant AI experiments’ and for the ‘development of robust AI governance systems’, three major international standard-setting organisations—the IEC, ISO and ITU—stressed that standards can ‘underpin regulatory frameworks and […] provide appropriate guardrails for responsible, safe and trustworthy AI development’. At the EU level, negotiations are advancing on finalising the AI Act, where standards are highlighted as a modality to demonstrate conformity with the act’s legal provisions. CEN, CENELEC and ETSI are already working on such standards. In the UK, the new  white paper on AI regulation notes that ‘technical standards can provide useful guidance on good practices for AI governance’.

The European ENISA issued recommendations for standardisation organisations, government agencies and policymakers regarding digital identities. 

The US government released the National Standards Strategy for Critical and emerging technology, which was the focus of the Biden administration’s digital agenda. The European Union followed suit. 

On the relationship between standards and human rights, the Office of the High Commissioner on Human Rights ran a public consultation event and issued a call for contributions to inform the upcoming report that the High Commissioner will present to the Human Rights Council at its 53rd session. And when the World Standards Cooperation leadership (i.e. heads of IEC, ISO and ITU) met in February, the importance of integrating human rights into international standards was one of the key messages.

At the same time, SDOs—nationally and internationally—have continued working on standards for advanced technology, from the US National Institute of Standards and Technology (NIST) having adopted an AI Risk Management Framework to the ITU’s Focus group on the Metaverse having held its first meeting.

Global Digital Compact process issued an assessment from deep dives and consultations. The assessment recognised the significance of interoperable internet standards and protocols and the need to avoid internet fragmentation.

Different jurisdictions across the globe have reviewed the landmark DABUS case and continued its journey, with the UK Supreme Court agreeing with the decisions taken in past years from the USA, South Africa, and the European Patent Office that AI cannot be considered as a patent inventor. 

These lawsuits indicate the need to implement effective laws that protect copyrighted works. In June 2023, the UK adopted its code of practice on copyright and AI, while Japan expressed its commitment in May 2023 to strengthen AI development while also ensuring copyright protection. On another note, South Korea stated in May 2023 that it aims to create new guidelines and standards for copyrights of AI-generated content by September 2023. However, South Korea’s Ministry of Culture stated in December 2023 that it will not grant copyright registration to AI-generated content.

A 2023 prediction that came true is that data was prominent on the development and trade agenda. For instance, in August 2023, India adopted the Digital Personal Data Protection Act (DPDPA), which, together with  EU General Data Protection Regulation (GDPR), ‘stands as paramount pillars in the global mission to ensure the security of personal data.’ On another note, Japan established the National Data Administration to coordinate and promote the construction of Data infrastructure systems. In the meantime, China released its draft guidelines for Regulations on Regulating and Promoting Cross-border Data Flows, aiming to ensure the free flow of data. This would only apply to international trade and marketing, among others, that do not contain personal information or important data.

The EU played a major role in data governance policy as the European Commission adopted the adequacy decision for the EU-US Data Privacy Framework, which concluded that the US ensures an adequate level of protection to that of the EU when transferring data from the EU to the US. Later in November 2023, the EU Council adopted the Data Act, which gives users and businesses access to data generated by using their products or services through a reinforced portability right and copying or transferring data across different internet of things (IoT) products. The EU Data Act also aims to protect trade secrets and intellectual property rights. 

Data flows in emerging geopolitics

A general trend has been for countries to store more data on their territory, especially critical data such as health records and digital identities of citizens. 

Many countries will have to balance data sovereignty and integration in the global economy. The more data they keep within national borders, the less they can benefit from the international digital economy and growth. Free flow of data will be essential for small and export-oriented economies.

Data sharing will be critical for dealing with global issues such as climate change. At the same time, data that is collected and processed locally can lead to new AI and open data services on a national or regional scale, which could support the growth of local economies and cut into the profits of some big tech companies. 

The interplay between digital interdependence and sovereignty

Sovereignty, whether digital, data, AI, or cyber sovereignty, will remain high on the agenda in 2023. Governments will want to extend their legal jurisdiction over digital activities on their territory and reduce the risks of negative security and economic spillovers from integrated digital networks.

Full sovereignty will be much harder to achieve in the digital world, though, because of how the internet works and how powerful tech companies are.

Approaches to digital sovereignty will vary, depending on a country’s political and legal systems. Legal approaches include national regulation and court judgments; technical ones vary between data filtering and frowned-upon internet shutdowns. 

The term sovereignty will also be used more often in the context of the digital self-determination of citizens and communities, mainly related to control over data and future AI developments. 

Digital interdependence will provide a reality check for initiatives for more digital sovereignty. It is supported by a strong drive of citizens, companies, and countries to be connected across national borders. It can even survive wars. During the Ukraine war, many interdependencies between the two countries have been cut, but it is still possible to exchange messages between citizens in Russia and Ukraine via the internet.

The shift to an online way of doing things had long been coming. Companies had already begun slowly experimenting with new work-from-home practices, perhaps once a month, maybe once a week. Employees rejoiced, but managers trod carefully.

In 2020, the Covid-19 pandemic changed everything. Workplaces were encouraged to shift to online work almost overnight. Employees set up shop in their living rooms. Zoom’s profits skyrocketed. 

As the pandemic began to release the world from its grip, the hybrid way of working and meeting (a mix of working face-to-face from the office, and online from home) emerged as the new norm. With it came a new set of policy considerations:

• How are online meeting tools handling the personal data of users, especially children, who have had to start making use of virtual classrooms?
• What are the risks and negative effects of surveilling performance (if companies really need to)?
• How should governments tackle the status of gig workers, a sector which exploded during the pandemic due to the high demand for the service, and the flexibility it offers?