The announcement that ChatGPT had successfully passed the US bar exam with flying colours and the multiple examples of AI-generated contracts and legal documents spread fear among lawyers that a "killer application" had arrived and that robots would wipe out their jobs.

Some countries prohibited the use of ChatGPT, and Google delayed the launch of its generative AI solution, Bard, due to regulatory concerns.

Since November 2022, I have been testing ChatGPT and, for a few days, Bard, now available in Europe. Both ChatGPT and Bard have extraordinary capabilities, though we might say that they have different "personalities" and respond differently to the same question. One cannot say that either response is fundamentally better than the other.

Testing ChatGPT

In one of my tests, I asked ChatGPT to "improve the clarity" of a "force majeure" clause. For laymen, a force majeure clause is a contract provision that releases a party from liability (breach or delay in the performance of a contract) caused by an unforeseen, abnormal and uncontrollable event, such as war, earthquakes, etc.

The original clause submitted to ChatGPT stated:

"No party shall be considered to have breached its obligations under this Agreement or be held accountable for any delay if such party's failure to perform or delay is caused, in whole or in part, directly or indirectly, by war (whether war be declared or not), emergency, strike, industrial dispute, accident, fire, earthquake, flood, storm, tempest, any act of God or any other similar cause beyond its reasonable control."

ChatGPT presented the following text:

"Neither party will be deemed to have violated their obligations or held responsible for any delays if the failure to perform or delay is directly or indirectly caused, in whole or in part, by circumstances beyond their control. These circumstances may include war (whether declared or not), emergencies, strikes, labour disputes, accidents, fires, earthquakes, floods, storms, acts of God, or any other similar causes that are considered beyond their reasonable control."

Some of the changes are irrelevant and do not improve the clarity of the text: "neither party" instead of "no party", "be deemed" instead of "be considered," and other changes, some of which are highlighted in the text above, seem innocuous.

Other changes, however, significantly change the text and the scope of what can be considered "force majeure". In its response, ChatGPT divided the sentence into two sentences to simplify readership. The first sentence defines "force majeure" as "circumstances beyond" the parties' control. The second sentence gives examples of the circumstances beyond the parties' control, broadly reproducing the list in the original text with small changes that do not seem to change the text materially.

To a non-lawyer, the meaning of the two texts would seem identical, but that is wrong. ChatGPT's text considerably expanded the definition of force majeure and the situations in which the defaulting party would not be liable for the breach of contract. In ChatGPT's text, any circumstances beyond a party's control would release it from liability. The examples of the second sentence serve as examples to clarify the meaning but would not restrict the meaning of "circumstances beyond their control".  

In the original sentence, "force majeure" only includes the events listed and other "similar" events. This means that the defaulting party would have to prove that the event causing the default was beyond its control and similar to the events listed in the clause. For instance, a delay caused by a supplier's default would be considered a force majeure event in ChatGPT's text but not in the original text because a supplier's default is not similar to an earthquake or a war.

The limitations (and dangers) of ChatGPT

This case is a good example of the limitations (and dangers) of ChatGPT. ChatGPT is a language model. The model identifies statistical patterns and relationships within its data set. ChatGPT "learns to predict the probability of the next word in a sentence given the context of the preceding words" (quote from ChatGPT).

In simpler words, ChatGPT generates text based on the information provided to it. This allows it to interpret a sentence and a request and give back an output based on the information that the model has digested from other texts. ChatGPT does not operate logically in the sense that we usually use the word "logic"; that is, ChatGPT does not "deduct" or "infer" on its own. ChatGPT compares and relates things in a different way than humans do.

Because ChatGPT feeds on information that is provided to it, if that information is wrong, incorrect or incomplete, ChatGPT's answers will be flawed. ChatGPT and other generative AI models are trained with large data sets to correct imperfections and further finetuned in specific subjects to eliminate errors.

Using our example above, ChatGPT can be taught that the general concept of "force majeure" is not, in principle, equivalent to any event outside the control of one party but to exceptional circumstances, thus avoiding misconstructions like the one cited above. However, this does not hide the fundamental fact: ChatGPT can generalize, can provide assertive answers, spot patterns and highlight differences, but (at least for now) ChatGPT cannot go to the deepest level of thought and identify a slight nuance that changes meaning in a fundamental manner. ChatGPT does not think. ChatGPT does not create.

This limitation can fundamentally impact how ChatGPT can be used to provide legal advice or draft a contract clause. If, in some cases, a change in a definition to include an element that is generally not within its usual meaning, although still acceptable, can be intentional, intent is not part of ChatGPT's construct.

ChatGPT may make suggestions that, while not being outright errors, can impact the ultimate result. A human must take the decision and bear the responsibility for accepting, rejecting or correcting ChatGPT's suggestion.

ChatGPT raises the bar for lawyers using it because they need to approve or correct ChatGPT's outputs. ChatGPT's suggested wordings are different from contract templates bought from a legal book of precedents. Lawyers have an extra duty of care when using ChatGPT. Lawyers have to decide if ChatGPT's suggestion is acceptable or not. Lawyers must turn ChatGPT's outputs into legal advice. So, while ChatGPT can massively improve the productivity of lawyers, when used without care it can lead to professional liability claims.

Lawyers must think and apply their knowledge and experience in providing legal advice based on ChatGPT's outputs.

Basic rules for using ChatGPT

The limitations and dangers of ChatGPT raise many issues beyond the general ethical and policy considerations that have appeared in the media.

The limitations and dangers of ChatGPT require a different approach and mindset when using ChatGPT and generative AI.

ChatGPT is a powerful tool. ChatGPT can lift heavy weights. ChatGPT can flatten the terrain like a bulldozer. ChatGPT can turn a stone into a perfect sphere or a perfect pyramid, but it cannot create La Pietà of Michelangelo. ChatGPT is a tool that can be like the chisel in Michelangelo's hands. We need to learn how to use it without harming ourselves and others.

For lawyers, ChatGPT can do a lot of the heavy lifting, ease work and help to achieve better results for clients. To do so, here are a few rules on how to use ChatGPT:

  1. Ask ChatGPT for information. Do not ask ChatGPT for advice.
  2. While ChatGPT's answer may appear valid and sound, check the sources of ChatGPT's results. Do a basic Google search and look for information from authoritative sources before using ChatGPT's outputs.
  3. Start small. Do not ask ChatGPT to draft a contract or provide advice. Ask ChatGPT to make minor changes to a piece of text. Ask to draft a paragraph with specific information. Given suitable prompts and using the right models, ChatGPT can help you achieve impressive results.
  4. Use ChatGPT to put you in the right direction. Do not ask for more than you can chew. If you do not know anything about a subject matter, learn about it before using ChatGPT's outputs.
  5. Build on ChatGPTs outputs. ChatGPT is a formidable tool. It can provide you with information almost instantly that will spark your intelligence and show different solutions (sometimes wrong) that make you think better about what you want to achieve.

To end, I asked ChatGPT to review these rules. Here is ChatGPT's answer:

Overall, the text is correct in providing guidelines on how to use ChatGPT effectively and responsibly for lawyers. It emphasizes using ChatGPT as a valuable tool to aid legal work and achieve better results for clients. Let's analyze each point:

"Ask ChatGPT for information. Do not ask ChatGPT for advice." This advice is sound. ChatGPT can provide factual information based on its training data, but it is not a substitute for professional legal advice.

"While ChatGPT's answer may appear valid and sound, check the sources of ChatGPT's results. Do a basic Google search and look for information from authoritative sources before using ChatGPT's outputs." This is a crucial point. Since ChatGPT generates responses based on patterns in its training data, cross-referencing its answers with reliable external sources helps verify accuracy and avoid potential misinformation.

"Start small. Do not ask ChatGPT to draft a contract or provide advice. Ask ChatGPT to make minor changes to a piece of text. Ask to draft a paragraph with specific information. Given suitable prompts and using the right models, ChatGPT can help you achieve impressive results." This is good advice to limit the scope of tasks assigned to ChatGPT. Starting with small, well-defined tasks can enhance the quality of the results and make better use of the AI's capabilities.

"Use ChatGPT to put you in the right direction. Do not ask for more than you can chew. If you do not know anything about a subject matter, learn about it before using ChatGPT's outputs." This is another important reminder. ChatGPT can provide useful insights, but users should have some foundational knowledge of the subject matter to evaluate and interpret the outputs properly.

"Build on ChatGPT's outputs. ChatGPT is a formidable tool. It can provide you with information almost instantly that will spark your intelligence, show different solutions (sometimes wrong) that make you think better about what you want to achieve." This point acknowledges the potential of ChatGPT as a valuable resource for generating ideas and exploring various perspectives. However, it also highlights that the generated responses should be critically evaluated before implementation, as they might not always be entirely accurate.

In conclusion, the text provides appropriate guidance for lawyers or any users using ChatGPT, promoting responsible and effective use of the tool to enhance their legal work and decision-making process.

 

 

According to local economic press, Novo Banco has started the process for selling BEST - Banco Eletrónico de Serviço Total, S.A. (“Banco Best”).

Banco Best is a digital platform operating in Portugal that provides a comprehensive range of banking products and services.

Banco Best was founded on 9 May 2001, as a result of a joint venture between Saxo Bank and the Espírito Santo Group. On 3 August 2014 and following the resolution procedure adopted by the Bank of Portugal on Banco Espírito Santo, its majority shareholder, Banco Best was included in the Novobanco’s group.

Banco Best operates as an online bank relying on its technological nature, based on national and international partnerships in the areas of Savings, Asset Management, and Trading. Overall, it operates as a universal bank focused on innovation and collaboration.

Banco Best serves clients from all private sectors with a diverse range of services such as banking, investment and savings solutions, financing, as well as day-to-day financial management. Its core business is related to investment and wealth management.

The bank offers a range of investment products, including mutual funds, exchange-traded funds (ETFs), and structured products. It also provides portfolio management services to high-net-worth individuals and institutional investors.

Banco Best is based in Lisbon and does not have physical branches. It provides its financial products and services via other channels, such as:

  • The Internet, through its website and mobile banking;
  • Investment Centres based in Lisbon, Porto, Braga, Aveiro, Leiria, and Faro, that rely on a network of Personal Managers;
  • A network of Digital Managers, a permanent management team providing services, normally at a distance, to Customers requiring specialized once-off assistance; and
  • The Call Centre, in addition to telephonic attendance, also intervenes in the opening of accounts via video call in a 100% digital process.

The bank has a network of business introducers and external advisors registered with the Bank of Portugal (Banco de Portugal) and the Securities Market Commission (Comissão do Mercado de Valores Mobiliários) that work as service providers.

Focusing on technology and innovation, BEST has implemented several initiatives to improve its digital offerings. For example, it has launched a robot-advisory service that uses artificial intelligence and machine learning to provide personalized investment advice to customers.

Banco Best, which is reported to have between 75,000 and 95,000 clients has had a significant growth in recent years. In 2021 the bank recorded a 41% growth in client acquisition and recorded a net profit of EUR 3.3 million, a growth of 83% compared to the previous year.

According to the latest available financial statements, on 31 December 2021, Banco Best recorded total assets of €860 million, of which €584 million of investments in credits institutions, €148 million in loans to clients, €67 million of cash and deposits and €43 million of financial assets.

Based on the 2021 financial statements, the bank presented the following ratios:

  • Core Tier 1: 44,1%.
  • Liquidity Coverage Ratio (LCR): 124%;Cost to income: 78,6%.
  • Leverage ratio: 8,9%.
  • Loan-to-deposit: 20.3%.

In 2021, Banco Best had an equity position of EUR 82 million. If we consider a price-to-book ratio of 0.70, the bank’s approximate valuation would be less than EUR 60 million.

According to the media, Novobanco has retained the services of Arcano and KPMG to organise the sale of Banco Best and a teaser has already been disclosed to potential investors.  

Banco Best offers an interesting opportunity for players looking to acquire a digital bank fully licensed in the EU with a team and a client base that operate in a digital environment. As a setback, Banco Best may come with a legacy of technological choices that may not go in the direction of emerging digital banking technologies.

This article was published by Expresso, a Portuguese newspaper, on April 1

There is no doubt that the world is at a turning point, in History, in the Economy, and in the lives of us all. In History, the veil is now falling away that for so long prevented us from recognizing one of the greatest tyrannies on Earth (and don't think that Russia is the only one that we have yet to admit as such, as we still have China and countries like Saudi Arabia, which we continue to treat as equals in values when they are not). In the Economy, we have entered an inflationary cycle, which was already inevitable as a consequence of the monetary policies followed in the fight against the effects of the Covid-19 pandemic. And which, with the Russian invasion of Ukraine, nobody can tell where it will lead us. In the lives of us Westerners, fortunate enough to live far from war and poverty, we feel squeezed by the rising prices of everything we consume and perplexed in our lack of understanding of the price-setting mechanisms. Some call for the taxation of capital gains that they adjectivize as unjustified, immoral, and the cause of the famine that affects the majority. Others, more moderate, question the universality of market rules and wonder whether it is not time for a new chapter in Economics too.

In this dire context, the European Commission recently proposed a plan called REPowerEU to erase dependence on Russian fossil fuels before 2030, to rebuild European gas reserves and to address rising energy prices in Europe. This initiative might, besides shaking the gas market, have a significant impact on the renewables sector, as it aims at allowing member States to take price regulation measures, to impose temporary windfall taxes, and to use of revenues from emission trading and state aid mechanisms. In the Iberian electricity market we have also seen discussions about electricity pricing mechanisms. The electricity wholesale prices in OMIE (where the daily price and the intra-daily price of electricity in the Iberian Peninsula are negotiated) are calculated through on a marginal prices mechanism that tries to mirror the meeting of forces between the supply and demand for electricity. There is an algorithm for these calculations called EUPHEMIA (who knows if named after the Greek saint tortured to death for not agreeing to participate in pagan sacrifices in the Roman Constantinople of the 3rd century) and we can say in this regard things are very complex; but, trying to simplify them, the setting of electricity wholesale price at OMIE works as follows:

OMIE puts the demand indicated by the operators of the Spanish (REE) and Portuguese (REN) grids together with the offers made by all different types of Iberian producers. The price established for the purchase of the electricity will be the price of the last offer to be entered into the system (normally, that of those who has less incentive to sell, i.e., those who obtain a lower profit margin). If this last offer comes from a combined cycle gas power plant producer it will reflect the costs of this producer and not, for example, the average of the production costs of all the offers made that day. A photovoltaic plant producer will sell its electricity in OMIE at the selling offer price of the producer of the combined cycle gas plant. This, in the current context, means having a significantly higher margin than it would be willing to accept if all the offers to the market were from photovoltaic production.

Here one may ask whether if, by aggregating different types of offers and choosing a price-setting criterion that seems incapable of reflecting the different production costs, we are not preventing the market from functioning properly as it would if the direct confrontation between comparable offers and demand was possible. Of course, the choice of the marginal prices’ principle has a technical explanation, a rationale that may seem more appropriate in a context of abundant supply and homogeneous costs (where the pressure to sell is similar for all producers) but it is apparently necessary because the system needs the energy produced by gas and other fossil fuels burning producers.

The creation of a special tax on renewable generation sources to match the so-called windfall profits (in the style of the infamous claw-back tax created by the Portuguese Government to eliminate the “unjustified” profits of Portuguese producers in MIBEL compared to the Spanish, victims of a special tax of 7%) implies a disincentive to what we are all saying we want to encourage. A disincentive with not only immediate impact, but also for the future of investment in renewable energy marketplace, which needs fiscal predictability. It is important to remember that the market operates based on a perception of risk, which includes factors within the market itself, such as technological developments or, conversely, negative developments in the cost of production factors. If we add non-market risks, such as administrative pricing or the imposition of taxes, the market will be disrupted, affecting, without discrimination, the supply (with high costs producers having to close doors) and the demand (which may have to endure either higher prices or shortages of electricity).

Therefore, ideas like the setting of a price ceiling at 180 euros per MWh, as has been suggested to the EU Commission by the Spanish and Portuguese Governments, will result production at a deficit in gas-fired plants. Certainly, producers with higher costs will withdraw their supply from the market generating supply shortages, unless they are subsidized (making the measure useless). We would risk not having electricity for everyone, because, at the present moment, the energy supply is not elastic (much has been said in this regard about the Portuguese Government's haste in anticipating the closure of the coal-fired plants).

Because all the above results of prices following natural laws and having no ideology, any electricity prices’ regulation is to be avoided. And taxation on the so-called windfall profits will naturally cause prices to rise or electricity to be in short supply for everyone. The least harmful way of State interference will be the direct support to those consumers who are least able to bear the increases in electricity market prices: the individuals and small companies with the fewest resources and the electro-intensive consumer companies whose activity is indispensable to the country's economic fabric. And the most efficient way of providing such support will always be paying individuals and companies in cash (and never by granting them new credit lines, the equivalent to offering water to a drowning person); or, better yet in the case of companies, offering them direct tax rebates.

Consequently, the EU Commission and the EU member States should, first of all, give priority to a consensual reassessment of the electricity pricing models and, if possible, adjust them so that they allow the market to function better, because it is not the market that is failing, but possibly the rules to which trading platforms like OMIE are subject to.

Many companies still limit the scope of their corporate accountability and ethics to merely complying with the relevant legal obligations. Profitability remains the main, if not the only, criterion (in many cases) governing business decisions.

Social, legal, and regulatory changes, however, are forcing companies into adopting a different approach. Companies must now provide clear disclosure of their financial position and corporate governance practices and carry out transactions transparently while ensuring to safeguard competition. They must also respect all human rights, prohibit any employment discrimination, and act in a socially and environmentally responsible way, with sustainability and ESG (Environment, Social and Governance) appearing as an aggregating "slogan" of this current trend, which is (rightly) here to stay and with due visibility.

Corporate governance, corporate social responsibility, and compliance must work in unison in today's world. Traditional views on competitiveness and profitability are changing. The change will be vertiginous.

Of course, many of these issues have long been regulated, but control of corporate practices by other stakeholders has been growing. Clients, suppliers, employees, and society are paying far greater attention to the way companies behave socially and requiring them to meet specific criteria, which place them at a different level of competitiveness. The competitiveness of a business and its marketplace vis-à-vis other competitors will also depend on this.

Companies must review their governance practices not only to comply with their statutory obligations but to ensure accountability, fairness, and transparency towards their stakeholders.

Compliance challenges and changes

Companies are also facing new challenges in diversity management and equal opportunities to increase the proportion of minorities and women in senior roles.

Diversity management focuses on valuing ‘difference’ and on non-discrimination and respecting every individual in the workplace regardless of their race, gender, or sexual orientation. Antiharassment, which recently gained strength with the “#MeToo” movement, is another concern driving the introduction of new workplace policies and procedures.

We have also seen a surge of new laws and regulations about business ethics, social responsibility, and personal data, among others.

Social responsibility and sustainability — recognising a company’s role in society through, for example, charitable support and environmental responsibility — should not be seen as a marketing tool to maximise future profits but as contributing to the welfare of all stakeholders: employees, shareholders, suppliers, customers, and society.

Ethics are an essential and complementary part of compliance

Investors are changing how they review a company’s performance and make decisions based on criteria, including ethical considerations. There is evidence that a company’s ethical corporate behaviour is increasingly impacting stakeholders’ market perceptions and the decisions of investors and customers regarding their choice of companies to deal with.

In companies with poor culture and ethics, employees tend to behave in a way that can lead to unethical, harmful behaviour, increasing the risk of breaches and subsequent damages.

Companies will be obliged to assume responsibility for their management and employees’ actions unless they can prove that they have performed all endeavours to deter or advise against illegal and fraudulent behaviour.

Therefore, all employees must be given the relevant training, and controls are developed across the company involving all departments, primarily legal and compliance. Policies, procedures, or rules will not be effective unless they are prepared, implemented, and enforced in a much more inclusive manner within the company.

The key is not only to follow the law but to teach those within the company that doing so is not a choice. The company must understand why it must be followed and why it must be a business priority.

Compliance is not a passing trend

Compliance cannot be reduced to a set of checklists. There is no one-size-fits-all compliance solution.

Legal and compliance departments must develop a framework for promoting corporate ethics and legal compliance within the company. These steps include:

  • Implementing internal legal audits;
  • Making information regularly available within the company regarding corporate social responsibility and legal compliance;
  • Internally relaying relevant information about local and other legislation that relates to the business;
  • Providing training courses/workshops on corporate ethics and legal compliance for every single employee and discussing misconduct prevention across the company; and
  • Creating corporate ethics and legal compliance helpline, i.e., an internal whistle-blowing system.

Companies must understand that corporate governance, social responsibility, and compliance affect the entire company, including the board, management, shareholders, employees, and other stakeholders. It is becoming a day-to-day exercise for which they must be fully prepared.

It is time for companies to rethink legal compliance beyond traditional risk management and see it as a strategic business asset. Accountability, transparency, and dialogue can help make a company more reliable and boost the standards of other companies at the same level. Everyone benefits, but not necessarily in the traditional sense of profit!

In 1996, Nick Szabo coined the term “smart contract” in a revolutionary article on the introduction of digital technology in the realm of contracts. In that article, Nick Szabo stated: “[n]ew institutions, and new ways to formalize the relationships that make up these institutions, are now made possible by the digital revolution. I call these new contracts "smart" because they are far more functional than their inanimate paper-based ancestors. No use of artificial intelligence is implied. A smart contract is a set of promises, specified in digital form, including protocols within which the parties perform on these promises.”[1]

Since 1996, the emergence of blockchain technology has allowed the creation of a new form of legal ledgers which are run in a decentralised manner.

There are various classifications of smart contracts and smart legal contracts depending on whether they are fully or partially automated and recorded in a blockchain system or not.[2]  In this article, we will use the expression “smart contract” in its simplest and widest form.

We define smart contracts as computer instructions that represent the intention of the parties to create an obligation, make a payment, purchase an asset or service or trigger an event that has a legal consequence.

The primordial example of a smart contract is a vending machine. By inserting a coin in a vending machine, the person who inserted the coin purchases a snack or a beverage from the vending machine owner or operator. Automated ticketing machines are also old automated or self-executing contracts, whereby a person acquires the right to use a transport service, enter a movie theatre etc.

More recently, online contracts with Amazon and the like are also forms of automated purchase agreements that fall into the concept of “smart contract” because they allow clients to purchase goods and services by giving automated instructions through a machine.

In any of the above examples, there is an underlying “natural language” contract, that is, a language used by people and not coded instructions given to a computer. When we enter an online contract, we are often required to accept a standard contract, sometimes in a foreign language that we may not fully understand. This raises issues of the validity of those rules concerning general and standard clauses. We will not be concerned with these implications in this article; we will focus on the issue raised by “software coded contracts”, which is the widest possible definition of smart contracts.

“Software coded clauses” or “smart clauses” are computer instructions using software language that may constitute the performance of an obligation or trigger the verification of contract conditions. Software coded obligations are self-executing because, in most cases, they do not need human intervention. Software coded contract provisions are now used in all online contracts because every service or product purchased online triggers legal consequences, such as the obligation to pay and the obligation to deliver a service or good.

The entry and performance of online contracts have occurred without disrupting legal systems. Generally, around the world, legislations accept the validity of online contracts. Disputes have been resolved in a fairly satisfactory manner because suppliers that value their clients are ready to solve complaints in a friendly way. Customers dissatisfied with suppliers simply cease to purchase from those suppliers. The rules of supply and demand that govern mature and fair markets take the stress out of the system. However, some terms and conditions and the conduct of many online suppliers may not be legal on many occasions.

The buzz about smart contracts goes much deeper than simple online B2C online agreements, where software coded information is translated into service and purchase orders and money transfer instructions.

Smart clauses coded in self-executing software language can include complex payment terms and formulas, trigger conditions, default clauses and security enforcement provisions. Smart contracts can be used in all types of contracts, including very complex B2B contracts such as credit agreements, mergers and acquisitions, issuance, acquisition and disposal of securities, IPOs, financial derivatives, futures markets, restructuring agreements, construction contracts etc.

Also, matters of technical nature can be linked to the contract clauses through smart clauses, that is, technical parameters stated in legal contracts involving the operation of telecommunication networks, power grids, power production, software requirements etc. can be linked to the legal language of contracts and trigger contract consequences. Presently, many of those technical issues are left in the contract’s fringes and put into more vague and elusive contract terms, such as “best efforts” and reasonableness judgements, or left to mediation or litigation when they become unsolvable by the people dealing with the day-to-day operation of the contract.

There are five basic practical rules for ensuring that smart clauses are enforceable and do not raise even worse issues than natural language clauses.

First, smart clauses should be translated into a natural language. This means that every smart clause should have an equivalent natural language clause. The natural language clause should be as objective as the smart clause and not include open concepts that cannot be translated into the coded clause.

The need for this rule does not result from the Law but serves a practical need: clauses should be understandable by people without very deep knowledge of the law and the technical aspects of the contract. Judges and business decision-makers should be able to understand the key points of the contract.

Suppose the main clauses of the contract, like the performance of the contract, are dependent on a coded clause (with no natural language equivalent). In that case, it won’t be easy to understand why the parties chose that particular solution instead of another. Sure, there are contracts with heavy and complex technical issues, be that the legal formulation of the clause or the commercial and technical aspects. But, in most cases, the economic, commercial and technical terms have a “natural language” formulation inscribed in the agreements and understood by the persons present at the negotiation table, even when they include complex technical schedules.

Second, the content of smart clauses should be open and auditable. This means that the acceptance of the code should be made by experts of each of the parties. This requirement aims to give an equal footing to the parties. Smart clauses must be understood and controlled by the parties.

There should not be one party controlling the code and the consequences of the instruction generated by it. In present natural language contracts where the legal and commercial technicalities can be generally understood by the parties, each party should have its own legal advisors. In coded language contracts, an asymmetry in knowledge can be more damaging than not having legal counsel. Expert advice and verification procedures are necessary.

Third, smart clauses should be protected. Integrity is a key element of any contract. In natural language contracts, one of the parties cannot change the wording of clauses. This is ensured by putting the contract in writing and other formal requirements imposed by law or agreed by the parties. Tampering with the words of a contract means falsifying the contract content. The same rules apply to smart clauses and smart contracts.

However, because smart clauses are generally self-executing, the consequences of possible tampering with the contract software code are more direct and can unlock a chain of events that may be impossible to stop. For this reason, the integrity of smart clauses should be ensured.

Blockchain systems are an acceptable form of ensuring the integrity of contracts because the blocks of a blockchain cannot be changed without the agreement of the nodes of the system (all or a significant number of participants in the system depending on the type of consensus algorithm that is used). This ensures the integrity of the contract in a manner that is as efficient, if not more, than current government-sponsored or other centralised ledger systems. However, blockchain is not the only way to ensure integrity. The parties may appoint an independent third party to store and protect the code or even monitor its application.

Four, smart clauses triggering events that require human intervention should not be left to the parties. While many smart clauses rely on machine self-execution mechanisms, there are cases where human intervention is necessary to fill gaps or interpret the data. The parties should not take this decision.

For instance, if the contract stipulates that one of the parties must make a payment to the other if the temperature reaches 45 degrees and two official computer records state different temperatures, one 44.9 degrees and another 45 degrees, a decision will have to be made as to whether the payment condition was met or not.

This example underpins the fact that minor discrepancies in digital records or the non-existence of an independent digital record may require human intervention to verify or certify smart contracts trigger conditions. When that is the case, the person making that decision should be independent of either party.

In Ethereum, the contract parties may appoint persons, named “oracles”, to take decisions that will trigger or not trigger smart contract events. This is an adequate solution for smart contracts based on Ethereum. For smart contracts outside a blockchain, the parties may use independent entities and grant them the power to fill in the missing data or resolve digital records inconsistencies.

Five, contracts with embedded smart clauses should include effective and fast dispute resolution mechanisms. Smart contracts should contain dispute resolution mechanisms because smart clauses can add a layer of complexity for which courts are unprepared.

In existing b2c online contracts, few disputes are resolved in courts because their value is low. The consumer often simply refrains from purchasing from the vendor that failed to deliver. This is not the ideal way of resolving a dispute, and a more effective transnational redress system must be created.

In more valuable contracts, disputes can be taken to courts, but the time for resolution may be too long to remedy the harm suffered by one of the parties. Parties will trust more in contracts that contain safe and expedient means of resolution. These may include mediation and arbitration mechanisms that allow for taking over control over the code, stopping wrongful use of the code, correcting an improper use of the code and repairing or correcting the code that proved not to attain the parties’ goals.

Smart contracts are one of the greatest inventions of the turn of the century. They improve efficiency increase speed and quality of delivery.

Embedding smart clauses in natural language contracts and creating adequate dispute resolution systems backed by robust control and verification mechanisms are the first steps to make your contracts smart.

With the development of the digital economy, new economic and financial assets, like tokens and cryptocurrencies, were created. Because of their high (potential) returns, they have become a refuge for investors, leading more and more people to invest in them.
This type of asset is not subject to the limits of monetary and exchange rate policies defined and controlled by central banks, and this lack of regulatory control encourages volatility and speculation. The innovation of these instruments involves significant legislative challenges, particularly regarding their legal nature, the regulation of the respective market and the taxation of their holders’ profits.
Concerns such as money laundering and terrorist financing led to the publication of the report "Taxing Virtual Currencies", by OECD, in October 2020, which addresses the existing legislative gaps for the main types of taxes and gives countries that want to strengthen their tax policy in this area some recommendations. Among OECD's recommendations there was the need to provide guides on tax treatment of virtual currencies that are clear, regularly updated, and consistent with the treatment of other assets. In Portugal, unlike many other European countries, such regulation was not yet implemented.

But is there a tax regime in Portugal?

In Portugal, the law is silent as to how this type of asset is taxed.
Between March and May 2020, the purchase and sale of cryptocurrencies in Portugal increased by 60% compared to the same period in the previous year. However, against what would be expected, neither the Government nor the Parliament have been following this growth through a clear and adequate legislative framework.
More recently and following the announcement that the Bank of Portugal has taken over the supervision of entities managing cryptocurrencies and the approval of anti-money laundering rules specifically addressed to transactions on these assets, there have been rumors of a change in the position of the Portuguese Tax Authorities to consider that this income should be taxed as capital income (at a rate of 28% or 35% if from a "tax haven"). But no amendments have been approved (yet).

… so how are they currently taxed?

In the absence of an express taxation, and after being questioned by several taxpayers, Tax Authorities took the only position that would be acceptable under the law.
In what concerns Personal Income Tax (“PIT”), the Tax Authorities confirmed that the income from this type of assets is presumably not taxable, unless the income arises from the performance of constant, regular professional activity. However, it has not been clarified when there is a regular performance of a professional activity for this purpose, which creates uncertainty.
Tax Authorities have not yet disclosed any kind of understanding regarding Corporate Income Tax (“CIT”). But, as the taxable profit of legal persons is based on the net profit recorded in the company’s financial statements for the period and any income earned by a company must be registered in its accounts, the income arising from transactions on bitcoins should be subject to CIT.
Regarding VAT treatment of the transactions on bitcoins, Tax Authorities considered, following the understanding of CJEU in the Hedqvist case (C-264/14), that bitcoins are comparable to fiduciary currency and their exchange for fiduciary currency, or vice versa, carried out for consideration, although characterized as a supply of services for VAT purposes, will be exempt from Portuguese VAT.

What's next?

At the income tax level, very few countries have considered cryptocurrencies as fiduciary currency because they have limited acceptance, lack intrinsic value (they are not linked to the value of any commodity or foreign currency), are volatile, are not issued by a public authority and are not regulated.
The current tax framework for cryptocurrencies leaves Portugal on the (increasingly short) list of countries that still do not tax income from this type of asset, which makes Portugal an attractive destination for investors of this kind.
But it is difficult to imagine that these gains will escape the tax net in the future. The 2022 State Budget to be presented in the next two months could be a turning point and new tax rules could be approved starting January 1, 2022.

This article was published by Expresso, a Portuguese newspaper, on April 1

There is no doubt that the world is at a turning point, in History, in the Economy, and in the lives of us all. In History, the veil is now falling away that for so long prevented us from recognizing one of the greatest tyrannies on Earth (and don't think that Russia is the only one that we have yet to admit as such, as we still have China and countries like Saudi Arabia, which we continue to treat as equals in values when they are not). In the Economy, we have entered an inflationary cycle, which was already inevitable as a consequence of the monetary policies followed in the fight against the effects of the Covid-19 pandemic. And which, with the Russian invasion of Ukraine, nobody can tell where it will lead us. In the lives of us Westerners, fortunate enough to live far from war and poverty, we feel squeezed by the rising prices of everything we consume and perplexed in our lack of understanding of the price-setting mechanisms. Some call for the taxation of capital gains that they adjectivize as unjustified, immoral, and the cause of the famine that affects the majority. Others, more moderate, question the universality of market rules and wonder whether it is not time for a new chapter in Economics too.

In this dire context, the European Commission recently proposed a plan called REPowerEU to erase dependence on Russian fossil fuels before 2030, to rebuild European gas reserves and to address rising energy prices in Europe. This initiative might, besides shaking the gas market, have a significant impact on the renewables sector, as it aims at allowing member States to take price regulation measures, to impose temporary windfall taxes, and to use of revenues from emission trading and state aid mechanisms. In the Iberian electricity market we have also seen discussions about electricity pricing mechanisms. The electricity wholesale prices in OMIE (where the daily price and the intra-daily price of electricity in the Iberian Peninsula are negotiated) are calculated through on a marginal prices mechanism that tries to mirror the meeting of forces between the supply and demand for electricity. There is an algorithm for these calculations called EUPHEMIA (who knows if named after the Greek saint tortured to death for not agreeing to participate in pagan sacrifices in the Roman Constantinople of the 3rd century) and we can say in this regard things are very complex; but, trying to simplify them, the setting of electricity wholesale price at OMIE works as follows:

OMIE puts the demand indicated by the operators of the Spanish (REE) and Portuguese (REN) grids together with the offers made by all different types of Iberian producers. The price established for the purchase of the electricity will be the price of the last offer to be entered into the system (normally, that of those who has less incentive to sell, i.e., those who obtain a lower profit margin). If this last offer comes from a combined cycle gas power plant producer it will reflect the costs of this producer and not, for example, the average of the production costs of all the offers made that day. A photovoltaic plant producer will sell its electricity in OMIE at the selling offer price of the producer of the combined cycle gas plant. This, in the current context, means having a significantly higher margin than it would be willing to accept if all the offers to the market were from photovoltaic production.

Here one may ask whether if, by aggregating different types of offers and choosing a price-setting criterion that seems incapable of reflecting the different production costs, we are not preventing the market from functioning properly as it would if the direct confrontation between comparable offers and demand was possible. Of course, the choice of the marginal prices’ principle has a technical explanation, a rationale that may seem more appropriate in a context of abundant supply and homogeneous costs (where the pressure to sell is similar for all producers) but it is apparently necessary because the system needs the energy produced by gas and other fossil fuels burning producers.

The creation of a special tax on renewable generation sources to match the so-called windfall profits (in the style of the infamous claw-back tax created by the Portuguese Government to eliminate the “unjustified” profits of Portuguese producers in MIBEL compared to the Spanish, victims of a special tax of 7%) implies a disincentive to what we are all saying we want to encourage. A disincentive with not only immediate impact, but also for the future of investment in renewable energy marketplace, which needs fiscal predictability. It is important to remember that the market operates based on a perception of risk, which includes factors within the market itself, such as technological developments or, conversely, negative developments in the cost of production factors. If we add non-market risks, such as administrative pricing or the imposition of taxes, the market will be disrupted, affecting, without discrimination, the supply (with high costs producers having to close doors) and the demand (which may have to endure either higher prices or shortages of electricity).

Therefore, ideas like the setting of a price ceiling at 180 euros per MWh, as has been suggested to the EU Commission by the Spanish and Portuguese Governments, will result production at a deficit in gas-fired plants. Certainly, producers with higher costs will withdraw their supply from the market generating supply shortages, unless they are subsidized (making the measure useless). We would risk not having electricity for everyone, because, at the present moment, the energy supply is not elastic (much has been said in this regard about the Portuguese Government's haste in anticipating the closure of the coal-fired plants).

Because all the above results of prices following natural laws and having no ideology, any electricity prices’ regulation is to be avoided. And taxation on the so-called windfall profits will naturally cause prices to rise or electricity to be in short supply for everyone. The least harmful way of State interference will be the direct support to those consumers who are least able to bear the increases in electricity market prices: the individuals and small companies with the fewest resources and the electro-intensive consumer companies whose activity is indispensable to the country's economic fabric. And the most efficient way of providing such support will always be paying individuals and companies in cash (and never by granting them new credit lines, the equivalent to offering water to a drowning person); or, better yet in the case of companies, offering them direct tax rebates.

Consequently, the EU Commission and the EU member States should, first of all, give priority to a consensual reassessment of the electricity pricing models and, if possible, adjust them so that they allow the market to function better, because it is not the market that is failing, but possibly the rules to which trading platforms like OMIE are subject to.

5G – multi-partner business models

Around the world 5th Generation Mobile Network (5G) is expected to act as one of the main tools for economic recovery. By using shorter and higher frequency bands 5G promises lower latency, faster speeds, and greater carrying capacity, which will be especially relevant for accelerating transformation processes at the industry level and benefiting businesses and consumers.

As an evolution in the lineage of cellular mobile network, 5G upgrades its predecessor facilitating the remote control of machines by other machines and of countless day-to-day devices.

The advantages underlying the introduction of 5G vis-à-vis its predecessors include:

  • Higher-speed mobile internet access (around 100 times faster than 4G);
  • Remote control of machines and devices (IoT);
  • Enhanced possibility of network management for providers; and
  • Lower power consumption compared to earlier mobile technologies.

Although Portugal also shares these expectations, only in the beginning of 2022, ANACOM, the Portuguese regulatory authority, issued the rights to use the frequencies allocated to the winning bidders of the 5G Auction. Right now, the commercial exploitation of 5G is still at an embryonic stage.

Therefore, most market questions outstanding after the end of the auction, such as the role of the new players and new services to be implemented, remain unanswered.

In this context, while the technological advantages of 5G seem promising, it is not so clear how operators will be able to recuperate on their investments and, above all, how and when other industries will benefit from the technology.

For operators to both recover investments already made to acquire spectrum rights, as well as to deliver on the commitments that the licences require, they will need to develop collaborative, multi-partner business models with specific legal and regulatory challenges to overcome.

To be able to address these challenges, we will make a brief overview on some of the fields in which the boundaries between the communications sector and other undertakings will mostly fade.

5G operators' business models opportunities

From a regulatory perspective, until now, operators have essentially two options, which naturally will branch out almost endlessly. In the first junction operators will basically position themselves either at retail or wholesale level, with large operators, particularly legacy operators with widespread networks, operating in both levels.

In any case, they will be either (i) offering the network services they design to retail customers – either B2B or B2C – or, (ii) sublet network components to other network operators who, in turn, will offer them to their retail customers.

Simplistically it may be said that until the 1990’s explosion of commercially available IP based communications, in general, retail customers were users of networks focused on content, while operators focused on hard telecommunication engineering skills.

With personal computers exploding and broadband IP based services becoming ubiquitous, in the early 2000’s, the first over the top providers appeared, first in fixed services and a few years later, with the popularization of pocket computers, also known as smartphones using 2,5G and 3G, these services became fully mobile.

As discussed below, the technical possibilities offered by 5G, will not only speed up communications but allow retail customers to become value-added servicers themselves, further blurring the lines between users and providers.

Faster Internet speeds, increased traffic, and technology integration are the benefits commonly attributed to 5G. Some of the major benefits are:

Smart IoT devices - The number of Internet of Things (IoT) devices is expected to increase with the rollout of 5G speeds. Thus, IoT-focused companies may expect this technology to leverage their capabilities. From evolving infrastructure diagnostic systems, to providing better data insights and to reducing device vulnerability.

Network Slicing - The multitude of emerging technology uses and new services by businesses and consumers will require a flexible network that provides a better user experience. With 5G, users will be able to create multiple virtual networks with just one physical system. This network slicing may help enterprises provide an end-to-end virtual system, encompassing not only the network, but also the compute and storage functions.

Multi-Access Edge Computing - Through 5G technology, multi-access edge computing will help to relieve crowded enterprise networks, even while supporting hundreds of devices simultaneously. This cloud-based network architecture can also boost the overall performance of enterprise networks. In addition to handling large data loads and delivering real-time results, multi-access edge computing will also protect user data.

Therefore, we will highlight some of the main sectors (industries) that are usually credited with more immediate benefits from 5G and what could be the relationship between companies operating in the respective sectors and the operators.

Automotive sector

Among the various sectors, despite being one of the sectors that tends to benefit most from the implementation of 5G based networks, the automotive sector will be face some of the major challenges in implementing the “5G transformation”.

When talking about autonomous vehicles used in closed circuits, e.g. in logistics facilities such as warehouses, factories or even ports and airports, the improvements may be immediate since many vehicles may be connected to a network with very low latency and very high speed, which, connected to an intelligent system, will allow internal displacements to be increasingly efficient, fast, controlled and safer.

However, despite being one of the most promising sectors, many questions may emerge, such as: who will be responsible for possible accidents in case there is a failure in the network supply to the company that in turn indirectly affects the final consumer; who will be held liable for compensation if a product fails due to a connection fault; and who will be held liable for compensation in the event of a data leak, the company providing the service, or the operator?

Manufacturing and farming

5G is set to enable large scale “machine to machine” communications, allowing for a reduction in human error and an increase in automated processes. Also, using 5G real time communications to the operators of machinery is growingly possible, making the process faster and safer, with sensors that can reveal exactly when and where a tool needs changing or updating.

As well, in this emerging technological world, scientific farming techniques are being used to boost productivity in farms. These include use of Agri-IoT sensors for soil monitoring, water management, smart irrigation, crop health monitoring, drone-based farm management etc.

Deployment of 5G networks will provide added benefit to manage these drones and obtain real time data from the sensors and conveying it directly to farming operators.

Healthcare sector

In the healthcare sector app-based services are seen as a major tool to provide better services, thus it could benefit greatly from the introduction of 5G. Long-distance monitoring and care services which, although not being exactly novel, with the recent pandemic, we are getting a first glimpse of the possibilities.

5G will also allow for faster and more reliable real-time access to health data from wearable technology and even bring closer the reality of remote treatments. The possibility of using augmented and virtual reality (VR) tools will certainly assist with the provision of remote medical services.

Despite the countless benefits, this is one of the sectors that may raise more complicated situations to deal with, as: e.g., in case of an error due to a network collapse, who will be held responsible? Who bought the system that will serve as the base for the infrastructure, or the telecom operator?

The truth is that although the introduction of 5G will raise several legal and regulatory questions super-fast connectivity will allow futile things that we still do today, such as pushing the grocery cart, to disappear.

The importance of operators in connecting 5G with these sectors

With the 5G journey just beginning, disruption and innovation is already happening in the B2B segment.

The telecom operator of the future will not just be a broadband/communication provider but will be a partner to jointly develop digitization and automation solutions.

Telecoms are collaborating with a growing number of customers in the transport and industrial sectors, and more are to come. Such customers include railways, utilities, and companies in sectors such as energy, utilities, transportation and logistics, healthcare, as well as companies offering traffic management and drone operations.

Industrial campuses are where digitalization and automation are happening

Communication between machines and personnel/staff equipment (e.g., laptops, tablets, etc.) is traditionally implemented through local area networks (LAN) using Ethernet and Wi-Fi-based solutions. While LAN can provide high-speed communication, it is limited to fixed devices and cannot be used in extreme environments such as high temperature areas (e.g., factories producing steel, glass, etc.) and environments with a large number of moving elements (e.g., packaging and shipping warehouses).

While Wi-Fi is easy to install and use, it has a number of limitations. Typically, only a few dozen devices can be connected to a Wi-Fi network and the quality of Wi-Fi is unreliable, vulnerable to external factors (including interference from nearby Wi-Fi networks) and is a "best effort" network. This implies that Wi-Fi is not suitable for machine or mission-critical data flows.

5G field networks can supply the basis for industrial automation

Technology enabled by telcos can open radically new ways of doing business. For the first time, telcos have a valid justification to talk directly to business unit heads and offer them tailored potential innovative solutions based on the field network to further expand industrial productivity.

In such a role, the telecom operator not solely be the provider of the network but become an active partner in digitization and automation solutions with greater synergies with the underlying telecom infrastructure, resulting in lower costs for the industrial partner. In this way, the telecom provider will further move away from its typical role as an external cost centre to become a partnership-based "value creator" for the industrial customer.

Many companies still limit the scope of their corporate accountability and ethics to merely complying with the relevant legal obligations. Profitability remains the main, if not the only, criterion (in many cases) governing business decisions.

Social, legal, and regulatory changes, however, are forcing companies into adopting a different approach. Companies must now provide clear disclosure of their financial position and corporate governance practices and carry out transactions transparently while ensuring to safeguard competition. They must also respect all human rights, prohibit any employment discrimination, and act in a socially and environmentally responsible way, with sustainability and ESG (Environment, Social and Governance) appearing as an aggregating "slogan" of this current trend, which is (rightly) here to stay and with due visibility.

Corporate governance, corporate social responsibility, and compliance must work in unison in today's world. Traditional views on competitiveness and profitability are changing. The change will be vertiginous.

Of course, many of these issues have long been regulated, but control of corporate practices by other stakeholders has been growing. Clients, suppliers, employees, and society are paying far greater attention to the way companies behave socially and requiring them to meet specific criteria, which place them at a different level of competitiveness. The competitiveness of a business and its marketplace vis-à-vis other competitors will also depend on this.

Companies must review their governance practices not only to comply with their statutory obligations but to ensure accountability, fairness, and transparency towards their stakeholders.

Compliance challenges and changes

Companies are also facing new challenges in diversity management and equal opportunities to increase the proportion of minorities and women in senior roles.

Diversity management focuses on valuing ‘difference’ and on non-discrimination and respecting every individual in the workplace regardless of their race, gender, or sexual orientation. Antiharassment, which recently gained strength with the “#MeToo” movement, is another concern driving the introduction of new workplace policies and procedures.

We have also seen a surge of new laws and regulations about business ethics, social responsibility, and personal data, among others.

Social responsibility and sustainability — recognising a company’s role in society through, for example, charitable support and environmental responsibility — should not be seen as a marketing tool to maximise future profits but as contributing to the welfare of all stakeholders: employees, shareholders, suppliers, customers, and society.

Ethics are an essential and complementary part of compliance

Investors are changing how they review a company’s performance and make decisions based on criteria, including ethical considerations. There is evidence that a company’s ethical corporate behaviour is increasingly impacting stakeholders’ market perceptions and the decisions of investors and customers regarding their choice of companies to deal with.

In companies with poor culture and ethics, employees tend to behave in a way that can lead to unethical, harmful behaviour, increasing the risk of breaches and subsequent damages.

Companies will be obliged to assume responsibility for their management and employees’ actions unless they can prove that they have performed all endeavours to deter or advise against illegal and fraudulent behaviour.

Therefore, all employees must be given the relevant training, and controls are developed across the company involving all departments, primarily legal and compliance. Policies, procedures, or rules will not be effective unless they are prepared, implemented, and enforced in a much more inclusive manner within the company.

The key is not only to follow the law but to teach those within the company that doing so is not a choice. The company must understand why it must be followed and why it must be a business priority.

Compliance is not a passing trend

Compliance cannot be reduced to a set of checklists. There is no one-size-fits-all compliance solution.

Legal and compliance departments must develop a framework for promoting corporate ethics and legal compliance within the company. These steps include:

  • Implementing internal legal audits;
  • Making information regularly available within the company regarding corporate social responsibility and legal compliance;
  • Internally relaying relevant information about local and other legislation that relates to the business;
  • Providing training courses/workshops on corporate ethics and legal compliance for every single employee and discussing misconduct prevention across the company; and
  • Creating corporate ethics and legal compliance helpline, i.e., an internal whistle-blowing system.

Companies must understand that corporate governance, social responsibility, and compliance affect the entire company, including the board, management, shareholders, employees, and other stakeholders. It is becoming a day-to-day exercise for which they must be fully prepared.

It is time for companies to rethink legal compliance beyond traditional risk management and see it as a strategic business asset. Accountability, transparency, and dialogue can help make a company more reliable and boost the standards of other companies at the same level. Everyone benefits, but not necessarily in the traditional sense of profit!

A shorter version of this article was published by Público, a Portuguese newspaper, on January 18. To read, follow this link

 

The idea that robots and machines might one day replace people fascinates and scares many people. Literature, movies and cartoons depict the image of robots that take over control over humankind in a not-so-distant future. The Matrix saga, 2001: A Space Odyssey, The Jetsons, among many others have populated the imagination of children and adults for generations. Until the beginning of the XXI century, the subject of artificial intelligence (AI) was confined to the academic world, science fiction, and a few industries. At the end of the last century, Goggle brought AI to everyone’s lives in a palpable way. Research at our fingertips replaced long hours in libraries and bookshops.

Today, AI is everywhere, in social networks, in the advertising industry, computer research, development of cars and other machines among so many other things. Computer software is powered by AI engines. Smartphones, computers and laptops have embedded AI. When you lift a smartphone, unlock your phone using face ID or use speech recognition, you are using AI-powered software.

But the AI revolution seems not to have reached the business of law. Of course, lawyers and law firms now use AI in their electronic devices and in computer software, some of which is designed specifically for lawyers, such as document management systems and billing software. But AI has not disrupted the business of law as it has done in so many other businesses.

The changes to the business of law brought about by legal AI technology, the concerns and scepticism of lawyers call for a discussion about the role of legal AI in the future and if some or all of the lawyers’ tasks will be replaced by legal machines.

First, let us define AI. According to the Encyclopaedia Britannica “artificial intelligence (AI) is the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings”. AI is the ability to simulate the logic of an algorithm by a machine. An algorithm is a finite sequence of defined instructions used to perform a computation. Algorithms are used as specifications for performing calculations, data processing, automated reasoning, automated decision-making and other tasks. AI gives machines the ability to perceive a given environment and to take actions to achieve the goals set by the machine’s program.

To some lawyers, this is impossible, at least for the more complex legal matters, because the business of law, whatever its shape and form, lives around “words”. From the dawn of history, enacting and enforcing laws has revolved around the use of “words”. Rhetoric and grammar have always been at the core of all legal professions. Words may be ambiguous and have multiple meanings depending on the context and order in a sentence. The interpretation of words appears to be a purely human activity.

However, due to its “prescriptive” nature, the Law implies simple deductive reasoning processes, which makes it ideal for AI “coding”. Putting it simply, the Law is not immune to AI; on the contrary, the Law is an ideal field for AI.

The good news for today’s lawyers is that we are far from the day when AI will take over their business. For that to happen, we must “code legal thought”.

To code legal thought one needs to create the processes that will allow machines to interpret laws, contracts and court decisions, which seems still far on the horizon because “words” and “sentences”, the matter of law, have many meanings, many times elusive, and open to manipulation by legislators, the politicians that make the laws, lawyers and even judges, who are no more than humans and, therefore, have sentiments, opinions and convictions to which they hold strong. Right and wrong are not clean-cut, are not yes and no, are not a series of 0s and 1s.

Yet, legal thought can and will be software coded in the not-so-distant future.

This is how it will happen. Firstly, AI will replace lawyers and other legal practitioners in the review of documents. Document review systems use machine learning technologies and pattern recognition technology to identify key contract concepts, tag clauses, court decision patterns, flag discrepancies and other patterns in the application and interpretation of laws and contracts, etc.

Lawyers are still needed to interpret the data coming out of computer systems and attribute meanings to those discrepancies and patterns. The machine will learn from the human lawyers’ interpretation, build new models, discern potential risks, etc.

Existing computer programs, like Luminance or Kira, already successfully help lawyers to conduct due diligences and provide advice to clients.

The second stage of legal AI will affect how courts prepare their rulings. AI-powered research systems already give judges and lawyers access to legal precedents concerning the specific subject matter of the case. In the future, AI will enable judges to narrow down the key elements of their decisions and offer them a roadmap for the decision-making process. Let us take a simple court decision such as determining if the court has jurisdiction over a particular matter that is put to it. Legislations around the world have a clearly defined set of rules for determining courts’ jurisdiction, which can be coded in computer language, that is, in an algorithm.

Some software systems, such as Lexis+, offer court decisions analytics and help lawyers to assess the likelihood of success of cases based on past decisions.

Future legal algorithms will help legal professionals to determine if matters follow into one legal category or another and how the law will be applied in specific cases. This will be one step away from determining the application of legal rules. Again, taking a simple example, if someone goes into another person’s property and it was not entitled to do so by law, such action falls under the legal concept of trespassing. These tasks will be done with an increasing degree of complexity, eliminating false positives, the application of conflicting rules and rights, the existence of exculpatory reasons to dismiss the application of a certain rule and the choice for another prevailing rule.

Many lawyers will argue that doing law has some specific features, such as the interference of sentiments and beliefs, which make it a non-computable task. AI can probe into statistics and the cold walls of legal statutes - they will say - but not into the hearts and minds of real people.

This is the wrong approach to legal AI. There are two areas where legal AI will struggle to master: an upper layer of present laws with their cultural, sentimental and political veneer that cover the law’s core rules. This veneer will be cleaned up by more powerful algorithms and the rationality of legal algorithms, uncovering a simpler and, therefore, fairer set of rules free of many of their present inconsistencies and conflicts.

As far as lawyers are concerned, legal technology and, in particular, AI systems will change the way they work but will require all of their ingenuity to interpret the complex legal issues that are needed to power legal AI. Lawyers and law researchers will have to break down the questions embodied in existing laws, contracts and legal precedents to map the AI systems of the future. Lawyers will also have to understand how to introduce queries into AI-powered systems and interpret the results brought to light by AI, formulate legal strategies and create legal documents, such as court briefings, contracts and opinions.

Legal AI will empower lawyers and clients. Legal AI will create faster and more efficient ways of completing all legal tasks. This is the case of knowledge management, documentation analysis, contract drafting, litigation review, preparation of court briefings. Legal AI will release lawyers from many repetitive and standardised tasks.

AI will disrupt the business of law. AI will lead to the disintermediation of legal services as it is now doing in other business sectors. In finance, for example, centralised exchanges will have to compete with the blockchain-enabled trustworthy peer to peer (P2P). The same will happen with many existing legal services. The traditional legal services will only be provided by lawyers when a trusted confirmation or reliable advice cannot be found in other sources.

Many lawyers view the disintermediation of other business sectors as unwelcome news, unaware that automated legal services have already taken a chunk of their old business. Automated services now offer many services that were exclusively provided by lawyers and paralegals a few years ago, such as invoice collections, automated contract drafting is now offered to business consumers and for low-value contracts. It is foreseeable that in the medium to long term, many legal services will be taken over by machines.

All legal professions will benefit from AI. Lawmakers will make better laws; judges will issue fairer judgements; lawyers will be able to perfect their court pleadings to a higher degree of efficiency and practicality. Many conflicts will be solved before being taken to courts because the odds, that is, the likelihood of success, will be against one of the parties in a clearer way, prompting that party for a settlement or simply to avoid litigation.

AI will not replace lawyers, but it will radically change the way lawyers provide services.

Legal thinking must remain in the sphere of lawyers because inside the core of all laws live values and values are non-computable. Values cannot be reduced to the mathematical formulations of algorithms. The creation and the application of law must, in the end, be made by humans and for humans.

Law is a science and a technique, but it is also an art and therefore cannot be reduced to mere algorithms. This is the limit of legal AI and the limit to any AI-powered technology.