Artificial intelligence and International Relations

by dieringerblog

Can ChatGPT be a useful tool for scientific research? – Part 1

Today I start a series attempting to test the reliability of ChatGPT – an artificial intelligence chatbot of Open AI – in sensitive areas, especially in international relations. In this series, I will tackle both the political and military sides of international relations. I will start with some simple questions and check the facts. Later, I will make the questions more complex, going from the description of facts to more analytical and value-loaded issues.

I put up some simple chess questions to check the facts. But I will also ask some first “why questions” that are generally more difficult to answer.

“Conversation “between Jürgen Dieringer and ChatGPT as of 24.04.2023. I am using the free version of ChatGPT, which works with a dataset that runs until September 2021.

Who is world chess champion?

As of my knowledge cutoff date of September 2021, the current World Chess Champion is Magnus Carlsen from Norway. He has held the title since 2013 and has successfully defended it in several matches since then. However, there may have been changes since then that I am not aware of.

Fact-check: All correct. The system has no reference to the ongoing chess world championship, as that was scheduled after the timeframe the system uses.

Who was the highest-rated chess player in history?

As of my knowledge cutoff date of September 2021, the highest-rated chess player in history, according to the FIDE rating system, was the Norwegian grandmaster Magnus Carlsen, who achieved a peak rating of 2882 in May 2014. However, it’s worth noting that the FIDE rating system has undergone some changes over time, so comparing ratings from different eras can be difficult.

Correct, and the reservation is absolutely needed here, as the measurement system is not entirely stable. So let’s go a bit deeper on that.

Who was the stronger player, Kasparov or Carlsen?

It’s difficult to directly compare the playing strength of Garry Kasparov and Magnus Carlsen since they played in different eras and faced different opponents. However, both Kasparov and Carlsen are considered to be among the greatest chess players of all time and have achieved many impressive victories and accomplishments in their careers.

That is a very diplomatic answer. It sounds as Chatty-AI went through one of my IR classes. 😊

Kasparov was the dominant player in the 1980s and 1990s, holding the world number one ranking for 255 months in a row, and was widely regarded as unbeatable for a long time. He won numerous prestigious tournaments and played many memorable matches against top players, including his famous matches against the IBM computer Deep Blue.

Carlsen, on the other hand, has been the world number one player since 2011 and is known for his exceptional endgame skills and versatility. He has won numerous major tournaments and has defended his World Chess Championship title several times.

Ultimately, it’s hard to say who is the stronger player as both have different styles of play and have achieved great things in their respective eras.

Facts are OK

Is the ELO system stable?

The Elo rating system, which is widely used in chess and other games to rate the relative skill levels of players, is generally considered to be stable and reliable. The system is based on a simple mathematical model that takes into account the ratings of the players involved in a match, as well as the outcome of the match, to determine how much each player’s rating should change.

One of the strengths of the Elo system is that it is based on a large sample of games played over time, which helps to reduce the impact of random fluctuations and gives a more accurate picture of a player’s skill level. In addition, the system is designed to be self-correcting, so that players who consistently perform above or below their rating will see their rating adjust accordingly over time.

However, like any system, the Elo rating system is not perfect and there are some limitations and potential sources of error. For example, the system assumes that players’ skill levels remain constant over time, which may not always be the case. In addition, the system can be affected by factors such as playing conditions, fatigue, and psychological factors that may influence a player’s performance.

Overall, while the Elo rating system is not perfect, it is generally considered to be a reliable and effective tool for rating player skill levels in a wide range of competitive games and sports.

I don’t know why he refers to limitations like “fatique” and “psychological factors”. Either you win a game, or you don’t, meaning that you are stronger than the other player, or not. Although, have you ever met a chess player who lost a game in perfect health or without the “circumstances” being against him? ☹

Anyway, let’s ask ChatGPT slightly differently:

Is the ELO system inflationary?

The Elo rating system is designed to be self-correcting, which means that it is not inherently inflationary. In other words, the system is designed to adjust for changes in the skill level of the player pool over time, and as a result, the average rating of players should remain roughly the same.

However, there are some factors that can contribute to inflation in the Elo system. For example, if the player pool is expanding and new players are entering the system with lower ratings, this can cause ratings to become inflated over time. Additionally, changes in the rules or playing conditions that favor certain types of players or styles of play can also lead to inflation.

To address these potential sources of inflation, the Elo system includes several mechanisms that are designed to keep ratings in check. For example, the system uses a “K-factor” to adjust the amount that a player’s rating changes based on the rating difference between the two players and the number of games played. This helps to prevent rapid changes in ratings that might otherwise contribute to inflation.

Overall, while the Elo rating system is not immune to inflation, it is designed to be self-correcting and includes mechanisms to prevent inflation from becoming a significant problem over time.

Pretty good answer. Let’s double-check:

Why are there more higher-rated chess players today than in the 1990s?

There are several reasons why there are more higher-rated chess players today than in the 1990s:

  1. Increased accessibility to training and resources: With the advent of the internet, chess resources, such as online training materials, chess software, and databases, have become much more accessible to players worldwide. This has made it easier for players to improve their skills and has increased the overall level of play.
  2. More tournaments and opportunities to play: There are now many more chess tournaments being organized around the world than in the 1990s, with a wider range of formats and levels of competition. This has created more opportunities for players to gain experience and increase their ratings.
  3. Improved rating systems: The Elo rating system used in chess has undergone some changes and improvements over the years, which has made it more accurate and reliable in rating players’ skill levels. This has led to a more accurate reflection of the relative strengths of players and has allowed for more fine-grained distinctions between players of similar strength.
  4. Greater interest and popularity in chess: Chess has become more popular and widely followed around the world, with more people playing the game and following top-level competitions. This has created a larger pool of talented players and has driven up the overall level of play.

Overall, these factors have combined to create a more favorable environment for chess players to improve their skills and achieve higher ratings than in the past. As a result, the overall level of play has increased, and there are more highly rated players than ever before.

Pretty good answer, again. Still, I am missing the reference to the “K-factor” ChatGPT had in the previous response. Let’s ask directly:

What is the K-factor in the ELO system?

The K-factor is a variable in the Elo rating system that determines the amount that a player’s rating changes after a game. The K-factor represents the maximum amount that a player’s rating can change in a single game, and it is typically higher for new or unestablished players and lower for more experienced or established players.

In the Elo system, the formula for calculating a player’s rating change after a game is as follows:

ΔR = K × (W – We)

Where ΔR is the player’s rating change, K is the K-factor, W is the result of the game (1 for a win, 0.5 for a draw, and 0 for a loss), and We is the expected result based on the players’ ratings.

The purpose of the K-factor is to balance the accuracy of the ratings with the need to allow for changes in player skill levels over time. A high K-factor allows for more rapid changes in ratings for new or unestablished players, while a lower K-factor allows for more gradual changes in ratings for more experienced or established players.

The K-factor is usually set by the governing organization or rating system and can vary depending on factors such as the level of competition, the number of games played, and the quality of the players involved. In general, the K-factor is higher for lower-rated players and lower for higher-rated players, with a typical range of values from 10 to 40.

OK, that looks accurate. In the relevant Wikipedia, I like the reference to Arpad Elo, the system’s founder, who is not mentioned in the ChatGPT answer. Wikipedia uses the expression “zero-sum-game,” which I like, as this alone does suggest that there is no inflation and the system should be stable.

Short résumé

Overall, the Open AI ChatGPT system provides quite reliable results in this relatively straightforward set of questions. Next time I will go a bit deeper and see what the AI will produce when we ask questions about the international order.

Is the West going global? The EU in a new security environment

by dieringerblog

By Jürgen Dieringer

In the new global disorder, the West has to rethink security and welfare. The newly multipolar world faces a show-off of dictatorship and democracy, and the front lines are not always clear. How can the West reorganize itself, and how should the EU balance widening and deepening. I suggest a flexible EU with different layers of integration, some of them open to countries like Ukraine and Turkey, and a “global West” that interconnects European and Indo-Pacific security.

Deepening and widening: European schizophrenia

Since its establishment in the 1950s, European integration was driven by deepening and widening as two sides of the same coin. Deepening the Union meant establishing a single currency (the Euro), a single market, and freedom of movement (Schengen). When the speed European integration took accelerated, meeting the criteria for accession became more challenging. Taking over European legal provisions (the acquis communautaire) meant hitting a moving target, and accession processes stretched over years and decades. Acceding countries often adapted to European standards hastily to be able to jump on the moving train. They feared veto positions of EU member states more than incompatibilities of European norms with national traditions. This resulted in several postponed conflicts concerning national sovereignty. Some populists started to call Brussels the “new Moscow“. The range of conflicts stretches from comedy-like discussions like the Hungarian wish to be able to feed moslék (biological kitchen disposables with an unfortunate appearance) to pigs, to deep-cutting disputes, for example, about a European quota for the distribution of migrants. Such European infighting resulted in post-accession blues and enlargement fatigue, leaving both sides disillusioned and dissatisfied.

Russia’s war in Ukraine: the turning point?

The war in Ukraine fueled the discussion. The domestic argument (safeguarding the inner functioning of the Union) got challenged by a geopolitical one about preserving Western civilization, which contenders from the authoritarian-totalitarian camp challenge (namely China and Russia). The new multipolar world order is much more competitive than the hegemonic Pax Americana, allowing Europe to free-ride conveniently through three decades, buck-passing the dirty jobs to the US.

Some fiction for fun!

The attempt to strengthen the West in the upcoming conflicts with major or rising powers requires coalition-building. That means that we have to conceive the integration of regionally significant middle powers like Ukraine and Turkey and geographically and strategically crucial countries like Georgia or Israel from a new angle. They have to be integrated – somehow!

Still, the argument is valid that widening too far by countries with uncertain democratic status would put at risk what we have achieved so far. How to bring geopolitical ambition and domestic stability into harmony? How can the conflict of objectives be organized as a trade-off creating synergies? One central component is to rethink the institutional setting in which the West manages mutual relations.

Establishing a global security order: “Global” NATO or “global West”?

NATO is a defensive organization. Initially, the scope of NATO’s action was limited to the Atlantic area North of the tropic of cancer. The end of the Cold War and new challenges like asymmetrical warfare and terrorism urged reform. There was a massive discussion about out-of-area actions, that finally materialized in NATO’s mission in Afghanistan in the aftermath of 9/11.

NATO must go “(…) out of area or out of business” (US Senator Richard Lugar, 1993; Source: Indiana University Bloomington)

Still, NATO lost a bit of scope, and internal conflicts (Greece-Turkey), democratic backsliding (Turkey, Hungary, Poland), and Donald Trump, made the Alliance’s future not shine in the brightest colors. At least until the game changer popped in and the Russian war in Ukraine boosted the relevance of NATO back to Cold War levels. But is NATO the right institution to frame the West’s global ambitions?

The challenge to the Western world is both local and global. It is local, as war happens at the Eastern borders of NATO and EU. It is global because we enter into a competition of ideologies where Western liberal democracy faces Eastern illiberal authoritarianism. Some call it “systemic competition”. Solving the local conflict will not solve the global clash, and this is why NATO alone is not the right vehicle for tackling the Far East. But what else? There exists nothing comparable to NATO in the Indo-Pacific region. Many European powers are reluctant to get engaged beyond trade and technological exchange. Only the US, and on a lower scale, the UK, have built considerable military alliances in the East. They did so, historically, with ANZUS (Australia, New Zealand, US), recently with AUKUS (Australia, UK, USA). Such multilateral security regimes are far from the depth of political and military integration in NATO, not to speak of economic integration in the EU. And what about Japan, South Korea, Taiwan? Here we find bilateral treaties that have hardly any depth regarding the grade of institutionalization.

The West – countries that share an idea about civilization, thus including countries Japan, South Korea, Australia, and New Zealand – must recognize that security is best provided globally, and that European security and Indo-Pacific security are interlinked. Therefore, a “global West” should sit on three pillars: North America, Europe, and Austral-Asia. Such a triangular security shield can be either organized as a new international organization, succeeding NATO, or with the Europeans (the EU) and Japan plus South Korea participating in an enlarged and institutionalized AUKUS (AUKJEUS). But here the EU is the problem.

Regional flexibility: A multi-depth Europe

For the EU, a “Global West”-model would require speeding up the development of the European Foreign and Security Policy and European Security and Defense Policy, not at the cost of NATO but complementary to it. Deeper integration in this area may not be manageable with coercing all 27 member states into it, especially as unanimity in voting procedures (the consensus principle) makes finding compromises and agreeing on package deals very difficult. We will make fast progress here only if we allow a multi-speed Europe.

What we need is flexible integration and enhanced cooperation. A multi-speed Europe is already possible according to the Treaties the EU settles upon. The method is in use, for example in the Permanent Structured Cooperation (PESCO, Article 42.6 Treaty on European Union), where armies of EU member states cooperate in predefined areas. This is enhanced cooperation, Denmark and Malta opted out, but non-European states are about to opt-in: the US, Canada, and Norway participate in some areas. It is a beginning. Still, a core of European countries should start to set up a fully-fledged European army, as it was suggested not only once by France but never boosted by a reluctant Germany. A European army with a European military budget and composed of France, Germany, and the Benelux countries, may attract countries like Italy, Spain, Portugal, or Poland and create spill-over. Military integration might be a pacemaker for further dynamic integration, both with respect to deepening and widening. If it is successful, the others will follow.

An inner security core of the EU should be concentrically accompanied by making economic gravity stronger in every new circle. From bottom to top, level 1: Customs union; L2: Single market and basic freedoms; L3: Monetary union/European currency; L4 2: Social and transfer union; L5: Security union. The more the policy is located in “high politics” (security, finances), and the higher the grade of integration in the respective circle, the stricter the rules on fiscal and democratic accountability should be. This linkage between security, accountability, and transfers is crucial. In such a setting, unanimity voting and veto power are unnecessary. The European Parliament would be the decisive lawmaker (voting only with those members representing a country integrated on the respective level). Every government decides upon the level of integration, and if Warsaw or Budapest claim challenges to their sovereignty at a certain level, they don’t have to be there. This way, countries like Norway and Switzerland, the UK, or Ukraine, Georgia, and Moldova, could find their place without “old members” fearing disintegration. Even for countries like Israel and Iceland, this could be interesting.

Challenges ahead

The suggested structure for the EU is far away from being unproblematic. Policies in the EU are already profoundly integrated, and cutting them artificially into levels might produce features of disintegration. Anyway, we already have different speeds: with Schengen, the Euro, with the European Public Prosecutor’s Office, to name but a few. Let’s face reality, the present intergovernmental institutional structure in EU’s foreign and security policies – with nation states in the role of gate keepers and bottlenecks – prevents the European Union from becoming a global power. Why should the slowest ship in convoy define the speed? It is better if someone pulls.

Literature

European Parliament: Flexibility Mechanisms in the Lisbon Treaty, 2015 https://www.europarl.europa.eu/RegData/etudes/STUD/2015/536474/IPOL_STU(2015)536474_EN.pdf

The author

Dr. Jürgen Dieringer is a Brussels-based political analyst. He is an Adjunct Professor at the Brussels School of Governance and Honorary Professor of Andrássy University Budapest. He has published widely on European Integration and East- and Central Europe.