Navigating the labyrinth of AI regulations

A wave of new regulations aimed at managing the impact of artificial intelligence is about to hit the corporate world across the globe.

This month, the EU's AI Act – a landmark piece of legislation to regulate the fast-evolving technology – has come into force across the 27-member bloc. The EU is leading the way, but it is not alone in the charge. A global regulatory push will unfold over the next two years, introducing a variety of new rules and requirements in many countries.

However, the first – the EU Act – is regarded as the world’s most restrictive among the forthcoming rules and could set a global precedent.

Multinational businesses are well-versed in handling international regulations, but the integration of AI into products and services, everything from search engines to advanced generative AI tools like ChatGPT, brings a new level of complexity.

AI regulations span at least 10 policy areas that include data protection and intellectual property, which vary from one jurisdiction to another, making managing of AI compliance one of the biggest challenges for the corporate world.

Given the still-evolving nature of AI regulations, companies must approach compliance even more carefully than usual while trying to maximise the benefits of AI and avoid the risks of non-compliance. The advantages of AI include enhanced efficiency and innovation, while the risks of non-compliance entail legal penalties and reputational damage to the business.

The St Gallen Endowment’s Digital Policy Alert – the public repository of policy changes affecting the digital economy – provides valuable insights into these new and sometimes landmark AI rules, and in the past year, the alert system has reported more than 440 new regulatory developments affecting AI.

This surge in regulations has been driven by the rapid advancements in AI since the launch of ChatGPT in November 2022. The US, the EU and the UK are the most active jurisdictions, with 173, 94 and 52 regulatory actions, respectively.

These cover policy areas tracked by the Digital Policy Alert including design and testing standards, and consumer protection, as well as data governance rules that require companies to ensure their AI training data sets do not misuse personal data.

Other areas include competition and intellectual property, along with moderation rules that aim to prevent AI systems from generating harmful content and require companies to have mechanisms in place for its removal.

Though various jurisdictions around the world are experimenting with AI regulations independently, effective compliance across the globe requires tighter co-ordination.

Currently, only a few AI rules are well-known and understood by business leaders, including the now-in-force EU Act. America’s executive order on AI – signed by President Joe Biden in October – has received a mixed response from the corporate world.

The big concern in the US regulatory action is that the executive order lacks the legislative enforcement provided in the EU’s Act.

China, meanwhile, has enacted three specific AI regulations addressing generative AI, deep fakes and recommendation algorithms. And countries such as Argentina, Brazil, Canada and South Korea are also expected to introduce their own AI laws soon, adding to the global compliance burden on multinational companies that sell their products and services across borders.

The red tape across countries and policy areas also adds to the complexity for companies facing an expanding array of regulatory actions.

For instance, if a company operates AI-powered products and services across Asia, it must comply with China’s data regulations, India’s consumer protection laws and Australia’s online safety rules.

Navigating this patchwork of national rules is already challenging and AI’s numerous relevant policy areas only amplify this complexity.

This is a new challenge, even for multinational corporations experienced in dealing with established international rules. Different markets have their own emerging regulations across various digital policy areas, and enforcement agencies are applying them rigorously.

This year, California suspended Cruise’s permit for autonomous vehicle deployment due to non-compliance with quality standards, dealing a blow to the self-driving-car subsidiary of General Motors.

Enforcement primarily targets AI model developers such as Microsoft-backed OpenAI, rather than companies integrating AI into their operations. When ChatGPT was launched, it sparked numerous investigations by data protection authorities worldwide.

Competition authorities are scrutinising partnerships between AI providers to ensure fair practices. US regulators are also investigating potential political bias in Google’s Gemini AI system. Such probes can lead to big fines for AI-driven platforms found to have broken the rules, as the GM-owned Cruise example illustrates.

So, how should executives at such companies think about AI compliance strategies?

For one, they must integrate AI compliance risk into their strategic planning. Also, navigating the AI regulatory maze will require vast resources that are, in many cases, already dedicated to managing existing data governance rules. A reallocation is now needed.

Compliance teams must also understand the diverse challenges posed by varying rules across numerous regions and policy areas. This necessitates a broader focus beyond data protection to include all relevant policy areas of AI compliance.

Additionally, operational teams must adapt to the specific requirements of each market to ensure technical compliance. Because as AI regulations continue to evolve and spread to new jurisdictions, so too will the compliance challenges.

Tommaso Giardini is the associate director of the St Gallen Endowment’s Digital Policy Alert, a strategic partner of the International Institute for Management Development in Lausanne, Switzerland

Children who witnessed blood bath want to help others

Aged just 11, Khulood Al Najjar’s daughter, Nora, bravely attempted to fight off Philip Spence. Her finger was injured when she put her hand in between the claw hammer and her mother’s head.

As a vital witness, she was forced to relive the ordeal by police who needed to identify the attacker and ensure he was found guilty.

Now aged 16, Nora has decided she wants to dedicate her career to helping other victims of crime.

“It was very horrible for her. She saw her mum, dying, just next to her eyes. But now she just wants to go forward,” said Khulood, speaking about how her eldest daughter was dealing with the trauma of the incident five years ago. “She is saying, 'mama, I want to be a lawyer, I want to help people achieve justice'.”

Khulood’s youngest daughter, Fatima, was seven at the time of the attack and attempted to help paramedics responding to the incident.

“Now she wants to be a maxillofacial doctor,” Khulood said. “She said to me ‘it is because a maxillofacial doctor returned your face, mama’. Now she wants to help people see themselves in the mirror again.”

Khulood’s son, Saeed, was nine in 2014 and slept through the attack. While he did not witness the trauma, this made it more difficult for him to understand what had happened. He has ambitions to become an engineer.

STAY%2C%20DAUGHTER

%3Cp%3E%3Cstrong%3EAuthor%3A%20%3C%2Fstrong%3EYasmin%20Azad%3C%2Fp%3E%0A%3Cp%3E%3Cstrong%3EPublisher%3A%20%3C%2Fstrong%3ESwift%20Press%3C%2Fp%3E%0A%3Cp%3E%3Cstrong%3EAvailable%3A%20%3C%2Fstrong%3ENow%3C%2Fp%3E%0A

What sanctions would be reimposed?

Under ‘snapback’, measures imposed on Iran by the UN Security Council in six resolutions would be restored, including:

An arms embargo
A ban on uranium enrichment and reprocessing
A ban on launches and other activities with ballistic missiles capable of delivering nuclear weapons, as well as ballistic missile technology transfer and technical assistance
A targeted global asset freeze and travel ban on Iranian individuals and entities
Authorisation for countries to inspect Iran Air Cargo and Islamic Republic of Iran Shipping Lines cargoes for banned goods

More from Rashmee Roshan Lall

US VP candidate Kamala Harris and the complexity of racial identity

Beirut blasts: What do we do with the world's ammonium nitrate?

How the pandemic is testing the solidarity of the European Union

When it comes to peace, is the EU really a great power?

((Disclaimer))

The Liechtensteinische Landesbank AG (“Bank”) assumes no liability or guarantee for the accuracy, balance, or completeness of the information in this publication. The content may change at any time due to given circumstances, and the Liechtensteinische Landesbank AG is under no obligation to update information once it has been published. This publication is intended for information purposes only and does not constitute an offer, a recommendation or an invitation by, or on behalf of, Liechtensteinische Landesbank (DIFC Branch), Liechtensteinische Landesbank AG, or any of its group affiliates to make any investments or obtain services. This publication has not been reviewed, disapproved or approved by the United Arab Emirates (“UAE”) Central Bank, Dubai Financial Services Authority (“DFSA”) or any other relevant licensing authorities in the UAE. It may not be relied upon by or distributed to retail clients. Liechtensteinische Landesbank (DIFC Branch) is regulated by the DFSA and this advertorial is intended for Professional Clients (as defined by the DFSA) who have sufficient financial experience and understanding of financial markets, products or transactions and any associated risks.

10 tips for entry-level job seekers

Have an up-to-date, professional LinkedIn profile. If you don’t have a LinkedIn account, set one up today. Avoid poor-quality profile pictures with distracting backgrounds. Include a professional summary and begin to grow your network.
Keep track of the job trends in your sector through the news. Apply for job alerts at your dream organisations and the types of jobs you want – LinkedIn uses AI to share similar relevant jobs based on your selections.
Double check that you’ve highlighted relevant skills on your resume and LinkedIn profile.
For most entry-level jobs, your resume will first be filtered by an applicant tracking system for keywords. Look closely at the description of the job you are applying for and mirror the language as much as possible (while being honest and accurate about your skills and experience).
Keep your CV professional and in a simple format – make sure you tailor your cover letter and application to the company and role.
Go online and look for details on job specifications for your target position. Make a list of skills required and set yourself some learning goals to tick off all the necessary skills one by one.
Don’t be afraid to reach outside your immediate friends and family to other acquaintances and let them know you are looking for new opportunities.
Make sure you’ve set your LinkedIn profile to signal that you are “open to opportunities”. Also be sure to use LinkedIn to search for people who are still actively hiring by searching for those that have the headline “I’m hiring” or “We’re hiring” in their profile.
Prepare for online interviews using mock interview tools. Even before landing interviews, it can be useful to start practising.
Be professional and patient. Always be professional with whoever you are interacting with throughout your search process, this will be remembered. You need to be patient, dedicated and not give up on your search. Candidates need to make sure they are following up appropriately for roles they have applied.

Arda Atalay, head of Mena private sector at LinkedIn Talent Solutions, Rudy Bier, managing partner of Kinetic Business Solutions and Ben Kinerman Daltrey, co-founder of KinFitz