We are happy to share with our readers our selection for Frontex June 2023 Industry days.
Frontex explains what are its Industry days as follows:
“Frontex assists the EU countries in supporting the development of modern technologies for the European Border and Coast Community. As part of its mandate, Frontex regularly meets with industry, researchers, and experts from the Member States to provide a platform for discussion and help develop new technologies and innovations related to border control”.
Frontex, Announcements – “Report: Training and methodology consultancy on scenario building in the context of risk analysis for law enforcement”, 6 July 2023
Within the context and for these Industry days, Frontex was seeking “service providers capable of offering a tailor-made framework encompassing training, processes, methodologies, and tools in the context of risk analysis for law enforcement” (Ibid.).
We created and sent a proposal answering to the detailed request by Frontex (see Frontex, Announcements, “announcement” 23 May 2023). On this basis, we were selected for a “presentation in an online meeting” (Ibid.).
As a result, we were also selected to participate in the online Industry days of Frontex.
“Climate breakdown has begun” warned UN Secretary-General António Guterres in a statement released on 6 September 2023.
Globally, throughout the 2023 Summer, the world has lived through the beginning of the turmoil and havoc that climate change and related temperature rise bring. Repeated heatwaves, related air pollution “with knock-on effects on human health, ecosystems, agriculture and indeed our daily lives,” as stated by WMO Secretary-General Prof. Petteri Taalas, drought, mega wildfires, medicanes (Mediterranean hurricanes), climate-driven storms, hurricanes, devastating floods, have globally scarred the Summer (UN News, “‘Climate breakdown’ alert as air quality dips during heatwaves: UN chief” 6 September 2023).
If climate breakdown has commenced and if its start entails so many disasters, then we must imperatively begin proactive planning to protect us from havoc. Especially, we need to have a better idea of what is more likely to happen among the various scenarios and hypotheses identified and studied by the Intergovernmental Panel on Climate Change (IPCC). This will enable us to outline potential trends that will constrain our lives, governance, and geopolitics. In other words, we shall make a draft of the structure of the world and its polities, under likely conditions of climate change.
Thus, first, we shall stress where we stand exactly in terms of temperature rise caused by climate change. Then, using the March 2023 synthesis of the Sixth Assessment Report (AR6) of the Intergovernmental Panel on Climate Change (IPCC), we shall look at the climate change scenarios for the future, notably through the perspective of carbon budgets. We shall explore what that means at both the global level and individual countries’ level, with a focus on the largest emitters. Building upon this last point, we shall deduce future consequences. We shall notably wonder if, in the future, some states could try to force others to reduce their emissions rather than seek to cooperate.
Where we stand in 2023
In a nutshell, we have been living between 2011 and 2020 at 1.1°C above the levels of temperature that existed between 1850 and 1900, which are considered as the healthy norm. In 2022, the average global temperature was about 1.15°C in excess (UN News, “2022 confirmed as one of warmest years on record: WMO“, 12 Jan 23).
Earth had the hottest three-month period on record, with unprecedented sea surface temperatures and extreme weather.
The Summer (June-July-August) of 2023 was the hottest on record globally “by a large margin, with an average temperature of 16.77°C, 0.66°C above average” (Copernicus Climate Change Service, “Summer 2023: the hottest on record“, 5 Sept 23). August 23 was the warmest August on record, and its temperatures second only to July 23 (ibid.). It is estimated to be around 1.5°C warmer than the healthy norm (ibid.).
Hence what was lived over the last years and more particularly over the Summer 23 represents the start of a very concrete experience of what we can expect next.
The near-future reality will probably be worse than what we experienced over the Summer.
Other impacts are known, but can be insidious and will skyrocket. For example, houses so far perfectly fine, suddenly start showing cracks because of drought. This stems from the shrink-swell capacity or shrinkage and swelling of clayey soils (retrait-gonflement des argiles – RGA), one of the consequences of drought – as a consequence of heatwave – and floods on expansive soils (e.g. Géorisques). It hits all countries with such soils and dwellings built upon them are at risks. For example, in France, the government estimated in June 2021 that “10.4 million individual houses [were] potentially very exposed to the phenomenon” up from 4,27 million in 2017 (Cerema, “Phenomenon of shrinkage and swelling of clayey soils (RGA): definitions, impacts on structures and people and solutions for adaptation to climate change,” 14 April 2022). 84% of French communes have more than 50% of their houses exposed with a risk ranging from low to high (MNR, Reference systems for the resilience of buildings to natural hazards, July 2023).
As a result, direct costs in terms of reinforcement of houses or even relocation of dwellers will be high (Ibid.). Worse still, the capacity to carry out the work will need to be available in the proper timeframe, which may lead to local challenges and tensions. Furthermore indirect costs such as psychological impacts start being estimated as being far from being negligible (Ibid.) Meanwhile, roads may also be impacted, which will likely increase the challenge faced (ibid.).
The global impacts of the Summer 2023 on individual dwellings and roads are still to be evaluated.
As the Intergovernmental Panel on Climate Change (IPCC) assesses with high confidence:
“Every increment of global warming will intensify multiple and concurrent hazards”.
Where we could stand in the future: the IPCC scenarios and carbon budgets
On 20 March 2023, the IPCC released the synthesis of its Sixth Assessment Report (AR6). The latter highlights possible scenarios for climate change and temperature rise, each with varying likelihoods, according to what is potentially done in terms of emissions of carbon dioxyde (CO2) and more generally Greenhouse Gas (GHG).
Looking at climate change through carbon budgets
Carbon budgets
The simplest way to look at the problem of climate change and GHG emissions is to think in terms of carbon budget.
Imagine the planet endowed with the capability to store a certain amount of carbon dioxyde or greenhouse gas. Because it can store these gas, and as long as it can do so, then it can safely emit these gases in the atmosphere. Below a given amount of gas, which corresponds to the capacity of storage or carbon budget, despite emissions, the temperature of the planet does not change and remains within healthy norms. Once the storage has reached full capacity, then the carbon budget is spent, further emissions cannot be stored anymore and the temperature starts rising with its corollary of adverse and deleterious impacts. Hence, using this principle, for each level of temperature in excess, a remaining carbon budget, compared to what has been spent so far, is approximately calculated.
What must be understood is that the carbon budget of the planet is for ever. It cannot be exceeded without consequences in terms of temperature change. If we want to emit CO2 and other GHG again, without consequences, then the amount of GHG in the atmosphere must first be lowered, which would mean decarbonisation.
For example, if we want the temperatures to remain at 1.5°C in excess, with little or no overshoot (i.e. up to about 0.1°C above the scenario level for up to several decades), and with a 50% likelihood, then scientists best estimates tell us that starting in 2020 we had 500 GtCO2 left (AR6). If we limit in the meantime other GHG emissions, then the budget for CO2 can become 600 GtCO2 (AR6). Inversely if we emit a lot of other GHG then the budget for CO2 may become only 300 GtCO2 (AR6).
If we wanted to increase the probability to see the temperature in excess remaining within the bounds of 1.5°C, for example to 83%, then the remaining global budget would become 300 GtCO2 (Patrik Erdes, Carbon Budget Calculator).
This implies that all countries must reach at one stage net zero emissions.
What are the consequences in terms of way of life and governance?
The new art of governance for a country will thus be to integrate at all levels, in all policies and actions, a balance between the level of one’s GHG emissions with direct consequences in terms of way of life, on the one hand, and, on the other, the impact of contributing to the global overspending of the carbon budget, i.e. consequences in terms of temperature excess, climate change and then cascading and self-reinforcing effects. And that, of course, without forgetting any of the principles that historically and fundamentally rule the art of governing, such as legitimacy and providing security to citizens.
However difficult, the new art of governance under conditions of climate change, furthermore, to be efficient, demands that all countries act similarly in a considerate and responsible way.
Scenarios of temperature rise and global carbon budgets
Now, we have seen the general principles, more concretely, what are the remaining global carbon budgets for the various possible temperature increases highlighted in the AR6 until reaching net zero emissions (5 scenarios of emissions and 3 sub-scenarios) ?
Scenario description
Likelihood to reach the desired max warming
GHG emissions scenarios (SSPx-y*) in WGI & WGII
Global carbon budget / Cumulative CO2 emissions
Date for net zero
C1
limit warming to 1.5°C with no or limited overshoot (+0.1°C for up to several decades)
(>50%)
Very low (SSP1-1.9)
500 GtCO2 (SPM)
[2035–2070]
C2
return warming to 1.5°C after a high overshoot (+0.1°C-0.3°C for up to several decades)
(>50%)
720 (WGIII SPM2 p.18)
[2045–2070]
C3
limit warming to 2°C
(>67%)
Low (SSP1-2.6)
1150 GtCO2 (SPM)
C4
limit warming to 2°C
(>50%)
1210 GtCO2 (WGIII SPM2 p.19)
[2065–…]
C5
limit warming to 2.5°C
(>50%)
1780 GtCO2 (WGIII SPM2 p.19)
[2080–…]
C6
limit warming to 3°C
(>50%)
Intermediate (SSP2-4.5)
no net zero – in 2100, 2790 GtCO2 (WGIII SPM2 p.19)
C7
limit warming to 4°C
(>50%)
High (SSP3-7.0)
no net zero – in 2100, 4220 GtCO2 (WGIII SPM2 p.19)
C8
exceed warming of 4°C
(>50%)
Very high (SSP5-8.5)
no net zero – in 2100, 5600 GtCO2 (WGIII SPM2 p.19)
What does that let us expect globally ?
In 2019, global CO2 emissions from fossile fuel combustion and cement production stood at at 35,3 Gt, in 2020, because of the Covid 19, at 33,4 Gt, in 2021 at 35,5 Gt and finally in 2022, they reached 36,1 Gt ((Liu, Z., Deng, Z., Davis, S. et al., “Monitoring global carbon emissions in 2022“, Nat Rev Earth Environ4, 205–206, 2023).
Thus, not only we do not decrease our global CO2 emissions, but we increase them, which is exactly opposite to what should be done. In two years, we have used almost 14% of the remaining budget to have a temperature increase of 1.5°C.
The United Nations highlights the current “Climate Emergency” in their Emissions Gap Reports (link to the 2022 edition). Considering current policies, we are on track for probably worse than the 2.8°C temperature rise by the end of the century estimated by the UN (Ibid).
What does that mean for individual states?
Let us now look at the situation for some of the largest emitters, taking into account their population to estimate their specific carbon budget, using Patrik Erdes’ convenient Country Carbon Budgets Calculator (2019 population estimates).
Scenario description
Country
Country carbon budget (calculated according to 2019 population)
If emission remains flat compared with 2019, date at which the budget runs out (uncertainty on temperature rise as net zero was not reached)
How much (in percent) must country emissions be reduced per year (starting in 2021) to reach net zero emissions before the carbon budget runs out?
C1
limit warming to 1.5°C with no or limited overshoot (+0.1°C for up to several decades) – (>50%)
China
81.99 GtCO2
2028
2.43% – Year the budget runs out: 2052
US
18.85 GtCO2
2024
16,19% – Year the budget runs out: 2027
Germany
4.77 GtCO2
2027
8.05% – Year the budget runs out: 2033
Poland
2.16 GtCO2
2027
8.00% – Year the budget runs out: 2033
India
78.61 GtCO2
2050
1.70% – Year the budget runs out: 2079
Russia
8.31 GtCO2
2025
11.24% – Year the budget runs out: 2029
C3
limit warming to 2°C – (>67%)
China
188.57 GtCO2
2037
2.86% – Year the budget runs out: 2055
US
43.37 GtCO2
2029
6.45% – Year the budget runs out: 2036
Germany
10.98 GtCO2
2036
3.35% – Year the budget runs out: 2050
Poland
4.96 GtCO2
2036
3.33% – Year the budget runs out: 2051
India
180.8 GtCO2
2089
0.732% – Year the budget runs out: 2157
Russia
19.12 GtCO2
2032
4.59% – Year the budget runs out: 2042.
C4
limit warming to 2°C – (>50%)
China
221.36 GtCO2
2041
2.43% – Year the budget runs out: 2062
US
50.91 GtCO2
2030
5.44% – Year the budget runs out: 2039
Germany
12.89 GtCO2
2039
2.84% – Year the budget runs out: 2056
Poland
5.82 GtCO2
2039
2.82% – Year the budget runs out: 2056
India
212.24 GtCO2
2101
0.622% – Year the budget runs out: 2181
Russia
22.44 GtCO2
2034
3.89% – Year the budget runs out: 2046.
If countries do absolutely nothing, apart from India, it appears obvious that the largest emitters, even considering a carbon budget allowance related to their population, will all soon have spent their budget for a 1.5°C temperature increase. Furthermore, by 2030, if the U.S. does not reduce its emissions below the 2019 level, then it will also have spent its carbon budget for a rise in temperature limited to 2°C.
If an effort is done towards reducing emissions regularly to reach net zero, then the U.S. still runs out of carbon budget in 2027 for the 1.5°C scenario, and thus is on a course for more than 2°C globally.
The disparities in time to net zero emissions and efforts to reach this state in a context of national interest, competition for power, ideology demanding an ever-lasting growth, let us expect that, most probably, most states will not willingly make the necessary effort to reduce their GHG emissions.
Meanwhile, as we have seen above with the carbon budget, the new governance in a warmer world becomes more complex, with, as a result, more room for a host of tensions and challenges.
Furthermore, countries, their citizens and governments will have to bear the brunt, in terms of survival and legitimacy, of others’ actions in terms notably of GHG emissions.
As a result of these two nexusses, one direction that could be taken is a mammoth effort towards decarbonisation. The way the latter is endeavoured, its timeline, who is carrying it out and how, may create very different paths forward.
Conversely, in the absence of relatively rapid and consistent global decarbonisation, with States facing duress within their borders, given the repeated failure to cooperate effectively on the issue of GHG emissions, can we imagine a future where some States try to force others to reduce their emissions? This would mean war.
Scenarios considering this possibility should be envisioned, even though they may be perceived initially as unlikely.
In examining such cases, we would also have, for example, to take into account the very cost of a war in terms of GHG emission.
One such study focuses, for instance, on the first seven months of the war in Ukraine (Lennard de Klerk et al., Climate Damage Caused by Russia’s War in Ukraine, Initiative on GHG accounting of war, 1 Nov 2022). It estimates that the cost “totals at least 100 million tCO2.”
However large, this amount only represents 1.58% of the 2018 yearly GHG emissions of the United States and 0,72% of the 2018 yearly emissions of China.
However, the study does account neither for the diminution of emissions in Ukraine – if any – resulting from industrial and agricultural destructions, nor for the increase in GHG emissions stemming from changes in patterns of international flows, new production of armaments, or destruction of carbon sinks, etc.
Yet, for our purpose, to get a real idea of the cost of the war in Ukraine in terms of GHG emissions we would also need to consider the destruction of industrial activity and food production.
For example, and to give an order of magnitude, the collapse of the Soviet Union led to a fall of approximately 40% of GHG emissions (Jean-Michel Valantin, Menace Climatique sur l’Ordre Mondial, 2005). Indeed, considering the economic collapse of the countries of the former Communist bloc, in 2007 the emissions of these states “were still about 37 percent below 1990 levels” (Bill Chameides, “Did the Kyoto Protocol Miss the Target?“, The Green Grok – Archive, 12 Oct 2009). As far as agricultural activities and food production are concerned, we now know more precisely, that following the collapse of the Soviet Union we had a cumulative net reduction of 7.61 Gt CO2 from 1992 to 2011 in GHG emissions (Florian Schierhorn, “Large greenhouse gas savings due to changes in the post-Soviet food systems“, Environ. Res. Lett.14 065009, 2019)
Thus, if we consider on the one hand the order of magnitude estimated by the study of the increase of GHG emissions linked to the war in Ukraine, and on the other hand possible drop in emissions over many years consecutive to a collapse, then some countries could consider that the cost in GHG emissions of a war are worth destroying industrial, energetic and agricultural activity of other large emitters. This would, of course, mean they have such states have the power to destroy the activity of others.
Specific and detailed scenarios must be created to account for the possibility to see war used as a way to reduce the GHG emissions of others.
Climate change will bring numerous unsettling novelties, many of which will be dire. Only by lucidly anticipating and planning for these changes can we hope to survive and eventually reconstruct a more promising world.
In the 2002 post-apocalyptic-movie “Reign of fire”, the last human colonies are exterminated by dragons burning the remnants of already poor crops. In 2023, the emergence of an early and powerful El Niño event amid the planetary effects of global warming raises the question of its geopolitical consequences in a world rocked by the war in Ukraine and the U.S.- China rising tensions (Nat Johnson, “May 2023 ENSO update: El Niño Knocking at the Door”, NOAA Climate.gov, 11 May 2023).
There is also a risk that potential warming effect of El Niño during the two or three next years will certainly be a dramatic driver of the impacts of climate on water and food security at the level of social cohesion in many countries.
Thus, El Niño will also amplify the risks of interactions between its effects and current situations of wars, civil wars and migrations. Those climate-and-conflicts nexus are already creating dialectics between local, national and international tensions (Jean-Michel Valantin, “What are Climate Wars ?”, The Red Team Analysis Society, November 2, 2021 and “Will There be Climate Civil Wars?”, The Red Team Analysis Society, November 30, 2021).
So, the El Niño-climate change and artificial intelligence multiple upheavals happen in the same time. The damages that the climate change turbocharged El Niño is likely going to inflict at the global scale is also becoming “food for thought” in the geoengineering field that is itself boosted by AI (Fleur Doidge, “Using AI and Machine Learning to Kickstart Climate Fightback”, IT Pro, July 19, 2022).
So, there is a very strong possibility that the 2023 El Niño is going to interact with the AI and political geoengineering field.
El Niño, the war in Ukraine and the great agricultural destabilization
The Reign of Fire
The great heat wave and historical drought that hammers Spain since April 2023 affects 80% of the country’s agricultural production (Jennifer O’Mahony and Joseph Wilson“Drought will causes crop failures in Spain, farmers warn“, AP, April 13, 2023). In Asia, the April-May 23 continental heatwaves put harvest under a huge thermic and hydric stress. Between April and June, a monster of a heatwave stretches from China and India to Central Asia.
In the U.S, the historical mega drought keeps getting longer. Thus, it maintains its pressure upon the U.S. croplands in the Midwest and the Southwest (U.S Drought Monitor, 1 June, 2023). Meanwhile, in Canada, one of the world’s leading agricultural powers, mega wildfires have been ravaging the north of the country since the beginning of May. In the same timeline, the Pacific Northwest braces itself in the face of a major heatwave alert (“Canada on Track for its Worst Ever Wildfire Season”, Reuters, June 6, 2023).
It is in this climate and weather context that numerous weather centres warn of an early return of an El Niño cycle in 2023. El Niño events are cyclical climate-ocean events. They happen when the equatorial and tropical Pacific Ocean surface cyclically warms up for one to three years. The current cycle has begun as soon as June 2023. It is two to three months ahead of the March-April weather forecasts (“El Niño Southern Oscillation (ENSO) Diagnostic Discussion”, Climate prediction Centre-National Weather Service-NOAA, 8 June, 2023).
Enter the El Niño Dragon King
Regularly, those events trigger cascades of extreme climate events all around the world. The previous 2016 El Niño was historically powerful. The 2023 El Niño may very well be even more dangerous. This is because of the rapid worsening of climate change that will very possibly reinforce El Niño’s intensity. (Paloma Trascasa-Castro, “Four Possible Consequences of the El Niño Return in 2023”, The Conversation, 26 January 2023).
During an El Niño event, the equatorial Pacific Ocean may heat up to 3°, thus heating up the whole atmosphere. The singular aspect of the 2023-2024 El Niño is that it happens in a time of rapidly intensifying climate change. The atmosphere temperature is already 1.2° above the mid-18th century pre-industrial level. So, the El Niño peak temperature may very well temporarily heighten the atmosphere’s heat around 1.5° (“Global Temperatures set to Reach New Records in Next Five Years”, World Meteorological Organization, 17 May 2023).
In other terms, the combination of the 2023 El Niño with the already dramatic consequences of an accelerating climate change on agriculture, temperatures and water cycle has a humongous potential to place entire countries in regional or continental “danger zones” (Mark Lynas, Our Last Warning: 6 Degrees of Climate Emergency, 2020).
The geopolitical implications of this situation are gigantic.
Civil wars, migrations and international wars
As we have seen, on the international side, since its start on 24 February 2022, the war in Ukraine has disruptive effects on the international markets of cereals and of fertilizers. The war blocks the exports of an important proportion of the Ukrainian harvest. In Russia, financial sanctions have a similar effect on Russian cereals exports (Jean-Michel Valantin, “War in Ukraine, The U.S Mega drought and the Coming Global Food Crisis”, The Red Team Analysis Society, May 1, 2022).
From domestic food security tensions…
In an international context where extreme weather events hammer the crops in the main rice, wheat and maize production zones, the combination of the war in Ukraine, of climate change and of El Niño is going to exacerbate food insecurity in poor countries as well as in richer nations for the middle and lower class (Malau, “Study of ENSO on Agricultural food crop prices as Basic Knowledge to Improve Community Resiliency in Climate Change”, IOP Conference Series- Earth and Environmental Science, 2021).
However, these multiple national domestic tensions, as, for example, in Myanmar, Afghanistan, Syria, Yemen, southern Africa, Sudan, Ukraine, Pakistan are already spilling over (“A Global Food Crisis”, World Food Program). They do so by triggering massive internal and external flows of refugees (Jordi Paniagua, Marta Suarez-Varela, Federico Carril-Caccia, “Forced Migration and Food Crisis : A Coming Catastrophe”, Social Sciences Research Network-SSRN, 26 August 2022).
As it happens, it would be a mistake to “only” consider these countries. Indeed, the climate crisis is already fuelling the massive migration crisis that extends itself from Central America to the U.S border. As it happens, the climate crisis is literally desiccating Central America. It is driving hundreds of thousands of poor farmers as well as desperate urban poors to leave profoundly dysfunctional and dangerous countries to go North.
This migrant crisis is rapidly saturating the absorption capacities of the border camps as well as of a growing number of U.S cities and megapolis, such as New-York, Los Angeles, Chicago. This massive and uninterrupted flow turns the migration issue into a particularly dividing political issue. In this context, the political conflict between conservatives and liberals reaches historically and dangerously high levels (Claire Kobucista, Amelia Cheatam, Diana Roy, “The U.S Immigration debate”, Council on Foreign Relations, 6 June 2023.
However, one must keep in mind that those feedback loops between geopolitical and domestic tensions in a time of climate change are not new but has already started previously (Jean-Michel Valantin, “What are Climate Wars ?”, The Red Team Analysis Society, November 2, 2021 and “Will There be Climate Civil Wars?”, The Red Team Analysis Society, November 30, 2021).
Indeed, our planet is already 1.2° hotter than during the eighteenth century. As we have seen, there is a high risk that El Niño pushes this thermic ration higher. Thus, in a span of two to three years, global temperatures may climb from 1.2° to 1.5°. In that case, all the aforementioned tendencies will be exacerbated.
So, this dynamic will certainly trigger violent competitions in order to access food, water as well as colder latitudes. Those competitions will be “channeled” through those domestic-international dynamics and put them in overdrive (David Wallace Wells, The Uninhabitable Earth, Life after Warming, 2019).
Thus, the potential for, for example, “water civil wars” in the Middle East will combine with flows of refugees from Central Asia and Africa. Those refugee flows will try to reach Europe, Turkey and Russia. In America, the Central American refugee crisis will interact with the El Niño dry spells in a time of mega drought (Paloma Trascasa-Castro, “Four Possible Consequences of the El Niño Return in 2023”, The Conversation, 26 January 2023). And this “El Niño-mega drought nexus” will also interact with the overheated politics of the U.S 2024 presidential election.
In other terms, the world is on the verge of entering a global and planetary danger zone. Facing the rapidly escalating consequences of the El Niño interaction with our overheating planet, the issue of “emergency responses” appears as a very strong possibility.
Burning World meets Geoengineering
From Earth to “Burning and Flooding World”
However, as the Earth turns into a new planet. Called “Burning World” by Hélène Lavoix, we build upon her concept and turn it into “Burning and Flooding World” (Hélène Lavoix, “When Denial and Passivity Verge on Stupidity” – The Red Team Analysis Weekly – 9 January 2020 and Jean-Michel Valantin, « Adapting to the Burning World », The Red Team Analysis Society, November 9, 2020).
The basic characteristics of the Burning and Flooding World is that the biological beings, the habitats and the ecosystems are now fuel for the Burning World or potential drowning wrecks. As a result, this helps us to understand the coming new geography of our Burning and Flooding World.
For example, in a few year’s time, through the combination of accelerating climate change and El Niño, California, the West Coast of North America, the Amazon Basin, and Australia risk becoming zones of ash and soot. Those massive climate destructions will trigger immense geopolitical upheavals (Gwynn Dyer, Climate Wars, The Fight for Survival as the World overheats, 2011).
For example, the Amazon basin risks dessication and burning beyond any resiliency. If that happens, the planet loses a major water cycle regulator and biological reservoir. Thus the riparian countries will also lose the plantations forcibly installed through the burning of the primal forest (Mark Lynas, Our Last Warning: 6 Degrees of Climate Emergency, 2020).
Losing this agricultural capacity will have massive consequences for China, because it imports massive quantities of Brazil soybean. Thus, it will put under stress the social cohesion of the 1.4 billion strong Asian giant (Cede Silva, “Lula and Xi sign 15 agreements on trade, agriculture, new satellite”, The Brazilian Report, April 14, 2023 and Genevieve Donnellon-May and Felipe Porto, “Brazilian soybeans and China’s food security”, The Strategist, 21 April 2023).
This will certainly entail emergency and survival politics (David Wallace Wells, The Uninhabitable Earth, Life after Warming, 2019). Those would be based on the combined imperatives of of the biological and social survival of nations and people. This follows the transformation from Planet Earth into “Burning and Flooding World” planet.
Indeed, through the cycle of the starting El Niño, there is a very high risk that Humanity is going to experience, at a global and collective level, what runaway climate change actually means.
AI World and the geoengineering issue
In this context, the “AI world” and its political, technological and industrial actors is going to defend itself. As a result, it will also protects the life conditions upon which it depends. One must keep in mind that the main AI actors are also quite keen at geoengineering schemes. Those are planetary technological schemes and devices.
For example, certain avenues of research are exploring the possibility to inject sulphur in the stratosphere. Other investigate the possibility to install space mirrors between earth and the sun, among other impressive projects (Clive Hamilton, Earthmasters – The Dawn of the Age of the Climate Engineers, Yale University Press, 2014).
One must keep in mind that experimental geoengineering schemes are currently massively proliferating. Indeed, dedicated research centres are installed in major universities such as Oxford, Harvard, and the University of Victoria in British Columbia. At the international level, the United Nations and other international bodies call for advanced research in the field (Alejandro de la Garza, “A Controversial Technology is Creating an Unprecedented Rift among Climate Scientists”, Time, March 17, 2023.
In India, China, Vietnam, the debate on geoengineering is raging. Meanwhile, geoengineering projects are also of utmost interest to oil and gas companies. This is especially true in the carbon capture field, as those companies expand their activities in Africa (GeoEngineering Monitor).
Many research bodies, as the IPCC, after having been strongly opposed to geoengineering, are now, cautiously, advising to study. They do so, as well as a growing number of scientists, because of the increasing danger posed by the climate crisis turning rapidly into a “long emergency” (Fred Pearce, “Geoingineering the Planet? More Scientists now say it Must be an Option”, Yale 360°, May 29, 2019).
In this context, the exponential emergence and diffusion of AI is a tipping point. Indeed, it generates new capabilities in order to calculate and to industrially master very complex mega projects. AI also generates piloting tools for very large scale technological devices (Hélène Lavoix, « Exploring cascading impacts with AI », The Red Team Analysis Society, May 17, 2023 and “Portal to AI-Understanding AI and Foreseeing the AI powered world”, and “Portal to Quantum Information Science and Technology- Towards a Quantum AI World ?” The Red Team Analysis Society. Thus, the AI development is of direct interest for geoengineering actors.
Furthermore, geoengineering projects and the technological spectre are intersecting with other fields in the wide domain of geo-technics such as mining, space exploration and satellite installation. As it happens, AI is already deeply embedded in theses ventures (Nguyen et al. Applications of Artificial Intelligence in Mining, Geo-technical and Geoengineering, Elsevier, 2023). It is also already and used by mining as well as by space companies.
However, the interactions between geoengineering projects and the mammoth complexity of the Earth-system and its crisis will certainly have unintended consequences. That’s why, since 2009 and the first sweeping academic report by the Royal Society, geoengineering has appeared as being potentially quite worrying. For example, one wonders what would be the consequences of solar “dimming” on the vegetation (Alistair Doyle, “Dimming Sunlight to Slow Global Warming May Harm Crop Yields: Study”, Reuters, 8 August 2018) ?
But, on the other hand, what will be the consequences of having no “planetary emergency measures” while El Niño fans the flames of “Burning World”?
Towards new international hierarchies
Moreover, the El Niño-climate change nexus turbo-charging geopolitics, geoengineering will be the equivalent of planetary politics led by an as yet unknown number of nations and industrialists. Thus, it will have tremendous geopolitical impacts. Indeed, it will create new divides between “pros” and “cons”, “haves” geo-engineering” and “haves not” and the “helped ones” and the “suffering ones”.
In this context, the AI power will be a powerful tool to help anticipating and mitigating those impacts. In other terms, the “AI world” will have to mobilize carefully a geoengineered world, in order to try to reduce the worst of “Burning World”.
And, as geoengineering systems will be “desperate measures for desperate times”, their conception begs the question of the politics and geopolitics of “what comes next”, in terms of political decision-making about geoengineering as in the strategic question of “what about the climate crisis after geoengineering”?
We created Sphinx, an AI assistant that will be your own personal “devil’s advocate”. Sphinx will assist you in challenging your assumptions and reinforcing your arguments, positions and sets of scenarios. Sphinx is now based on OpenAI’s GPT4-Turbo model*, further trained with The Red Team Analysis Society’s methodology and knowledge.
Start challenging your own assumptions with Sphinx. Don’t forget to also read why a devil’s advocate matters, and discover how Sphinx challenges us on climate change. Please note that OpenAI GPT4 -Turbo models ended their training in December 2023, and that for now, they do not browse the internet. Thus, apart from knowledge conveyed through RTAS articles, the AI assistants are not aware of news having taken place after December 2023.
Challenge your assumptions with Sphinx
Tips: * Check how to maximise interactions with AI. * Try! The first 7 queries (across all our AI assistants) are complimentary. For guests: in a form (Pithia), one click on submit [red button] = 1 query – In a chat (Aria, Calvin, Kai, Regina, Sphinx), 1 question and 1 answer = 2 queries.
Being able to challenge one’s hypotheses is indispensable in science. Indeed, in science we use falsification, i.e looking for an element, a fact, an event that would prove our hypothesis or explanation wrong. This is the only way to make sure our explanations, understanding, theories are valid (see, for example, Helene Lavoix, “Useful Rules for Strategic Foresight and Risk Management from Taleb’s The Black Swan“, The Red Team Analysis Society, 28 January 2013).
It is also fundamental, in strategy, to win.
One way to challenge our assumptions, is to use what is called a “devil’s advocate”. The term “devil’s advocate”, advocatus diaboli in Latin, also known as “Promoter of the Faith”, promotor fidei, comes from the practice in the Catholic Church, according to which
A dignitary “critically examined the life of and miracles attributed to an individual proposed for beatification or canonization… his presentation of facts included everything unfavourable to the candidate in order to uncover any character flaws or misrepresentations of their life of heroic sanctity.”
Britannica, T. Editors of Encyclopaedia, “devil’s advocate,” Encyclopedia Britannica, August 9, 2022
In contemporary usage, the term “devil’s advocate” refers to someone who plays a similar role in debates or discussions, by taking a position that is contrary to the majority view in order to identify weaknesses or flaws in the argument. As a result, s/he helps strengthen the overall position.
Facing an advocatus diaboli allows for challenging assumptions and stimulates critical thinking. In the context of strategic foresight and early warning, it is important to have a devil’s advocate perspective in order to identify potential blind spots or risks that may not be immediately apparent, and to ensure that all possible scenarios and outcomes have been thoroughly explored.
AI assistants that are built out of Large Language Models (LLMs) to hold conversations with human beings are very useful to play the “devil’s advocate” role. Furthermore, because they are not real people, then the emotional difficulty that may go with seeing one’s assumptions and beliefs challenged may be lessened. As issues of power and domination are removed when exchanging with an AI assistant, then we can more calmly ponder and reflect upon our ideas. As we get used to controversy and build more powerful arguments, then not only our cases, theories or strategies become more robust, but also, potentially, we may become stronger, calmer, more lucid and less stressed when facing opposition.
Case study: an AI devil’s advocate perspective on climate change
As example, we show here a session we had with Sphinx, challenging a belief, that is probably present in many people, regarding climate change:
User’s assumption: “Human beings have always overcome problems and our current civilisation is very advanced and enlightened. Thus, we shall have no difficulties continuing as we do and overcoming climate change.”
Sphinx: Let’s examine the hypothesis that human beings have always overcome problems and that our current civilization is advanced enough to overcome climate change. While it’s true that humans have a long history of overcoming challenges and progressing, it’s important to challenge this hypothesis and explore different perspectives. Here are some alternative viewpoints and questions to consider:
What if climate change is different from previous challenges that we have faced, both in terms of scale and urgency? Climate change is a planetary condition that impacts the entire biosphere and all human societies. Its effects will last for centuries, if not millennia. What if we are facing a challenge that requires unprecedented levels of global cooperation and collective action to address?
What if our current civilization is not advanced enough to overcome climate change? While our technological and scientific progress has been impressive, it has also created many of the problems we now face. Climate change is a symptom of a larger problem, which is the unsustainable use of natural resources and the degradation of ecosystems. What if we need to fundamentally change our economic and social systems to address the root causes of climate change?
What if we are already experiencing the impacts of climate change, and they are worse than we expected? The increasing frequency and severity of extreme weather events, rising sea levels, and biodiversity loss are all signs that the impacts of climate change are already being felt. What if we are underestimating the scale and urgency of the problem, and need to take more radical action to avoid the worst outcomes?
What if there are political and social barriers to addressing climate change that are difficult to overcome? Climate change is a deeply political issue, and requires concerted action by governments, businesses, and civil society. However, there are many interests that stand to lose from efforts to mitigate climate change, such as fossil fuel companies, and some governments and political factions. What if these interests are able to block or delay the necessary changes, making it difficult to address the problem adequately?
These are just a few alternative viewpoints and questions to consider when examining the hypothesis that human beings will be able to overcome climate change. It’s important to approach complex issues like this with an open mind, and to consider multiple perspectives and scenarios to develop a more comprehensive understanding of the situation.
Evaluating possible impacts is a key component of strategic foresight, early warning and risk management. It is crucial in strategy and, as a result, for strategic planning.
Go directly to Pithia to explore cascading impacts.
Very often we limit ourselves to thinking about the direct impacts of an action or of an event. Yet, impacts, most of the time, go on. We face cascading effects. For an event, a decision, we thus should consider first the direct impacts, then the second-order impacts (the direct impacts of the direct impacts), then the third-order impacts… until the nth-order impacts.
In terms of strategic foresight and early warning, the capacity to explore these nth order impacts is in-built into the use of a proper model. However this assume that such a model has been developed (see our related training course and how our AI assistant Calvin can help you in this regard), which is not always the case.
As an introduction to the importance of considering cascading impacts, we created an AI-powered form that allows you to explore some direct, second and third-order effects for an event or decision.
Pithia assists you in exploring 1st, 2d and 3rd-order impacts
Identify the primary decision or event and its context: the basis for your scenarios
Start by clearly defining the primary decision or event that serves as the basis for your scenarios. You can add context or constraints to obtain something more interesting.
For example, the primary event, decision or objective could be:
An EU’s pro-Taiwan stance within the context of Europe’s need for critical commodities.
or more simply US default on its debt
or Very rapid (less than 6 months) adoption of a generalised use of generative IA across companies, NGOs, governments, administrations and public services in the Western world
Determine the immediate or first-order effects
Use the AI assistant to identify direct and immediate effects of the primary decision or event. These effects should be directly attributable to the chosen objective or event. Find out what some of these effects could be:
Explore second-order effects
Next, consider the ripple effects or consequences that arise as a result of the immediate effects. These are the second-order effects. They may emerge as a response or consequence of the immediate effects.
Among those suggested by the AI, choose the immediate or direct effect you wish to explore, cut and paste it in the field below, amend it as you wish. You can also add a direct effect that was not mentioned by the IA. For example, your input could be:
EU’s pro-Taiwan stance: Improved European access to Taiwanese critical commodities: Taiwan is a key producer of critical commodities such as semiconductors and rare earth elements. The EU’s pro-Taiwan stance will improve access to these commodities, which are essential for European defense capabilities.
US default: Internationally, there would be a shift away from the US Dollar as the world’s reserve currency.
Generative IA adoption: Massive loss of jobs for humans. In general higher paid jobs would be more impacted than lower paid manual jobs notably of a craftsmanship type.The effect could be aggravated by the speedy adoption of AI, which would not give people enough time to adjust to the changes.
Discover third-order effects
Repeat the process by identifying additional effects that stem from the second-order effects. These effects should be logical extensions of the second-order impacts, considering the evolving dynamics and interdependencies between various factors.
Choose the second-order effect you wish to explore, cut and paste it in the field below, amend it as you wish. For example, your input could be:
EU’s pro-Taiwan stance: An increase in competition among other global players who rely on these Taiwanese critical commodities.
U.S. default: Significant diminution of the geopolitical power of the U.S.
Generative IA adoption: The employment situation could further exacerbate the already existing wealth gap between different groups in the society
Tips:Try! The first 7 queries (across all our AI assistants) are complimentary.
For guests: in a form (Pithia), one click on submit [red button] = 1 query – In a chat (Aria, Calvin, Kai, Regina, Sphinx), 1 question and 1 answer = 2 queries.
Tips: Training and examples We trained and tested the AI many times, notably on three issues. These are used as examples to guide you in the AI form.
An EU’s pro-Taiwan stance within the context of Europe’s need for critical commodities.
U.S. defaults on its debt.
Very rapid (less than 6 months) adoption of a generalised use of generative IA across companies, NGOs, governments, administrations and public services in the Western world. We pasted below the answers we received for this third example, with comments, considering the wide-ranging effects. The results the AI gives us are just elements of cascading impacts. A proper and real strategic foresight and early waning work should be built on a fully developed model.
Nota: This is an experiment with varying results. Some results given by the AI were excellent, others were less so. For example, it seems that the AI provided best results first. Then, if one asked the same question again, the results obtained did not improve massively or could even be less interesting. Comments and discussions on the results you obtained are welcome!
Current GPT-based apps break in terms of logic, consistency and ability to combine factors on different levels starting from the 4th-order effects. This appears to us as logical because they are “only” based on AI language models. As a result, even though GPT-based apps may appear able to reason, actually they cannot really provide analysis, which requires subjective reasoning. Nonetheless, as they are, GPT-based apps can already yield interesting results, which may become tools – to be checked and verified – for human beings.
The GPT4 model has increased capabilities and advancements but we are not yet into models with real reasoning capabilities. The future nonetheless may surprise us…
Evaluate the long-term implications
Consider the long-term implications of the scenario by examining how the multiple orders of effects interact and influence each other over time. Assess the potential outcomes and consequences on a broader scale, such as geopolitical realignments, economic shifts, or changes in regional dynamics.
Only you can do that, using all the tools available to us, and notably modeling. Maybe an AI in the future will also be able to do it, one day…
Case study – Cascading impacts for a very rapid adoption of generative AI
Output on cascading effects from Pithia (17 May 2023 – using previous GPT3.5 model)
Comments
Input Primary Event:
Very rapid (less than 6 months) adoption of a generalised use of generative AI across companies, NGOs, governments, administrations and public services in the Western world.
Pithia:
The direct and immediate effects of a very rapid adoption of a generalised use of generative AI across companies, NGOs, governments, administrations, and public services in the Western world could include:
Test 1
Massive displacement of jobs: AI could automate many jobs, leading to a significant loss of jobs for humans. The effect could be aggravated by the speedy adoption of AI, which would not give people enough time to adjust to the changes.
Increased productivity: AI could boost productivity in various sectors, leading to an increase in output and efficiency. Companies that adopt AI quickly could have a competitive advantage over those that don’t.
Privacy concerns: AI could collect vast amounts of data on individuals, raising concerns about privacy and surveillance. The speedy adoption of AI could exacerbate these concerns, as there may not be enough time to develop and implement privacy regulations.
Cybersecurity risks: AI could introduce new cybersecurity risks, as cyber attackers could use AI to launch more sophisticated attacks. The rapid adoption of AI could limit the time available to develop and implement effective cybersecurity measures.
Ethical concerns: AI could raise ethical concerns, such as bias in decision-making algorithms and the potential for AI to be used for harmful purposes. The speedy adoption of AI could exacerbate these concerns, as there may not be enough time to develop and implement ethical guidelines.
Economic benefits: The use of AI could lead to significant economic benefits, such as increased economic growth and reduced costs. The speedy adoption of AI could accelerate these benefits, leading to faster economic growth and development.
In summary, the very rapid adoption of a generalised use of generative AI across companies, NGOs, governments, administrations, and public services in the Western world could have significant and wide-ranging effects, including the displacement of jobs, increased productivity, privacy concerns, cybersecurity risks, ethical concerns, and economic benefits.
Test 2
The direct and immediate effects of very rapid adoption of a generalised use of generative AI across companies, NGOs, governments, administrations, and public services in the Western world would be significant and far-reaching. Here are some possible effects:
Job Displacement: The adoption of generative AI on a large scale will lead to the displacement of many jobs that are currently done by humans. This displacement will occur across all sectors, including manufacturing, services, and knowledge work. The impact will be felt across all levels of the workforce, from manual laborers to highly skilled professionals.
Increased Productivity: Despite job displacement, the adoption of generative AI will lead to increased productivity and efficiency in many areas. For example, tasks that are currently done manually, such as data entry or basic customer service, can be automated with AI, freeing up human workers to focus on more complex tasks.
New Business Models: The adoption of generative AI will enable new business models that were not previously possible, particularly in areas such as personalized medicine, online education, and predictive maintenance. These new models will create new opportunities for entrepreneurs and disrupt existing industries.
Regulatory and Ethical Challenges: The rapid adoption of generative AI will raise significant ethical and regulatory challenges that will need to be addressed. These include issues such as data privacy, bias in AI algorithms, and the potential misuse of AI for malicious purposes.
Geopolitical Implications: The adoption of generative AI by governments and military organizations could have significant geopolitical implications, as countries race to develop and deploy AI-powered weapons and surveillance systems. This could lead to increased tensions and a new arms race, as well as new challenges for international security and diplomacy.
Overall, the very rapid adoption of a generalised use of generative AI across companies, NGOs, governments, administrations, and public services in the Western world would bring both significant opportunities and challenges, with consequences that would be felt across all levels of society.
We knew the model used by GPT 3.5 was closed in September 2021, however our article Foreseeing the Future with ChatGPT? included the latest findings (March 2023) by OpenAi on the matter. Hence, beside testing the capabilities of the AI to identify cascading impacts, the question also allowed us to test the capacity of our IA to consider new knowledge existing on our website.
In general, the results obtained with the AI are interesting.
Notably in test 1 it accounts for the speed of adoption, but does not look at the geopolitical side, and does not detail the types of jobs that could be lost.
Test 2, for its part, specifies better the types of jobs impacted, but does not account for some of the findings of OpenAi: for example manual jobs will likely be less impacted than knowledge jobs. Yet, after checking the logs the AI indeed had access to this knowledge.
Test 2 mentions geopolitics but in a very general way.
Test 2 does not consider speed as a key factor.
Hence to obtain the best result we would need to mix the answers obtained with test 1 and test 2, added to our own specific knowledge and understanding. AI, as often in our case, is a tool that can help us and that we can usefully integrate within our work, but not a definitive panacea… at least not yet when using GPT-3.5.
Input direct effect: Massive loss of jobs for humansin the Western World.In general higher paid jobs would be more impacted than lower paid manual jobs notably of a craftsmanship type.The effect could be aggravated by the speedy adoption of AI, which would not give people enough time to adjust to the changes.
Pithia:
The massive loss of jobs for humans in the Western world due to the adoption of AI could have several significant impacts or consequences. Firstly, it could lead to a sharp rise in unemployment rates, which could result in social unrest, poverty, and inequality. This situation could further exacerbate the already existing wealth gap between different groups in the society.
Secondly, the economic impact could be significant, as the loss of jobs would mean a reduced purchasing power for consumers, leading to a decrease in demand for goods and services. This could result in a slowdown of the economy and reduced economic growth, which may cause ripple effects throughout the whole world.
Thirdly, the loss of jobs could lead to political instability, as people who are unemployed or underemployed may become more susceptible to extremist ideologies and populist movements. The rise in populist movements could cause political polarization and social unrest, leading to a breakdown in social cohesion and stability.
Furthermore, the adoption of AI could also have significant geopolitical implications. Countries that are less developed or have a lower level of technological advancement could be left behind, leading to an increased disparity between developed and developing nations. This could lead to a shift in global power dynamics, as countries with advanced AI capabilities may have a significant advantage over those that do not.
In conclusion, the rapid adoption of AI could have significant consequences for the Western world, including economic, social, and geopolitical impacts. These impacts could cause significant uncertainty and instability, and it is important to carefully consider the potential consequences of AI before implementing it on a large scale.
Here we have truly interesting potential second-order effects, that should definitely be taken into account worldwide by political authorities.
However, as far as our IA is concerned, we observe some difficulties to combine different second-order effects: for example, if in the Western world – those countries that adopt rapidly generative AI – the massive job displacement especially of better paid jobs leads both to unrest and to economic downturn, then will the countries having massively adopted AI still have a geopolitical advantage? Further, is it the very way we conceive the international society and the world order that could change?
Again, we are at too general a level to be able to truly use the results obtained to steer policy, yet, what our AI Pithia highlighted is definitely worth considering and incorporating in our analyses.
Input second-order effect: The employment situation could further exacerbate the already existing wealth gap between different groups in the society
Pithia:
The rapid adoption of generative AI across different sectors in the Western world could exacerbate the existing wealth gap between different social groups. This could happen as a result of massive loss of jobs, especially among those in higher-paying positions. This situation could be aggravated by the quick adoption of AI, giving people little time to adapt to the changes.
The consequences of this scenario could be far-reaching and complex. It could lead to social unrest and political instability, as people who have lost their jobs struggle to make ends meet. There could also be an increase in poverty and inequality, as well as a decline in the standard of living for many people.
Furthermore, the rapid adoption of AI could have geopolitical implications. Countries that are unable to keep up with the pace of technological change could be left behind, leading to a shift in the balance of power. This could result in increased tensions between nations, as well as a rise in protectionism and nationalism.
In order to address these potential consequences, it is essential for governments, policymakers, and businesses to take a proactive approach to managing the adoption of AI. This includes investing in education and training programs to help people acquire the necessary skills to adapt to the changing job market. It also involves being mindful of the potential social and geopolitical implications of AI, and taking steps to mitigate any negative effects.
Here the AI summarises well the situation, then stops short of truly continuing to look at specific and detailed consequences.
GPT 4 -Turbo (actual model – 16 Feb 2024) could be better at this task, or/and we need to improve how we handle the AI model to get better and more specific answers. Alternatively, LLMs – for now – may just not be able to properly handle such tasks and we would need different types of models.
Since its very outbreak in March 2022, the geopolitical and economic effects of the war in Ukraine have combined with the cascading consequences of climate change (Jean-Michel Valantin, “War in Ukraine, The U.S Mega drought and the Coming Global Food Crisis”, The Red Team Analysis Society, May 1, 2022). In 2023, it is very likely that this geopolitics-climate nexus will dramatically worsen. This stems from the emergence of what could very well be a turbocharged El Niño event combined with the disruptive effects of the war in Ukraine on global agriculture.
El Niños are cyclical climate-ocean events, which happen when the equatorial Pacific Ocean surface warms up for one to three years. Regularly, those events trigger cascades of extreme climate events all around the world. The previous 2016 El Niño has been historically powerful. The 2023 El Niño may very well be even more dangerous, because of the rapid worsening of climate change that will very possibly reinforce El Niño’s intensity (Paloma Trascasa-Castro, “Four Possible Consequences of the El Niño Return in 2023”, The Conversation, 26 January 2023).
In other words, the combination of the war in Ukraine and of climate change’s disruptions, especially in the fields of agriculture and food, are driving the massive “return of the repressed”, i.e. the capability of modern societies to meet the basic needs of populations on a rapidly warming planet, or not.
The war in Ukraine and the global fertiliser crisis
This happened because Russia and Belarus are leading producers of these essential products. The financial sanctions induced important difficulties for Russia and Belarus in exporting their fertiliser production. However, since the 2022 spike, fertiliser prices have been decreasing (Charlotte Hebebrand and Joseph Glauber, “The Russia-Ukraine war after a year: impacts on fertilizer production, prices and trade flows”, International Food Policy institute, March 9, 2023).
2023 as an agricultural danger zone
Throughout 2022 and the first quarter of 2023, facing the disruptions of the global fertilizer trade as well as the impacts of extreme weather events, several countries decided to limit or to ban the export of their own fertilizers production, or of basic components such as potash or urea. This was the case, for example, of China. Big importers, such as Brazil, India, Morocco, had to diversify their imports from other sources, Canada among others. Those systems of disruptions affect more than 20% of the global fertilizers trade (Hebebrand and Glauber, ibid).
This situation decreased the global availability of fertilizers. The most vulnerable countries, especially sub-Saharan countries, had problems to secure imports. This is pushing farmers to use alternate ways to fertilize fields, such as manure (Douglas Broom, “This is how war in Europe is disrupting fertilizer supply and threatens global food security”, World Economic Forum, March 1, 2023. Several international institutions, such as the World Bank, the African Development Bank, the World Food Program stepped in in order to help vulnerable countries importing fertilizers (Jeff Kearns, “Global Food Crisis may Persist, with prices elevated after year of War”, International Monetary Fund Blog, March 9, 2023).
However, diminishing uses of nitrogen and phosphates fertilizers mean high risks of 2023 diminishing crop yields. Trying to offset this risk, many farmers turn away from food crops to cash crops, such as tobacco. This approach is quite dangerous for those farmers, because they become dependent on the global markets prices oscillations (Kearns, ibid).
In the same timeline, Canada, and the U.S. government are strongly supporting the development of their domestic fertilizer production. The problem is that this production is heavily dependent on the prices and availability of fossil fuels (Charlotte Hebebrand and Joseph Glauber, “The Russia-Ukraine war after a year: impacts on fertilizer production, prices and trade flows”, International Food Policy institute, March 9, 2023).
From Germany to India vs fertiliser
This is especially true for Germany, whose chemical production feels strongly the huge impact of the loss of Russian gaz imports, because of the restrictions by Gazprom, the EU sanctions and the strange destruction of the Nord Stream 1 and 2 pipelines (“Germany says no results yet of Nord stream pipe lines sabotage investigation”, Reuters, 7 march 2023, and Thane Gustafsson, The Bridge – Natural gas in a redevided Europe, Harvard, 2020,).
In this context where agriculture, food security and geopolitics intermingle, it is worth noting that, during the September 2022 meeting of the Shanghai Cooperation Organization in Samarkand, the Indian Prime Minister negotiated at length fertilizers imports with the Russian President (Jean-Michel Valantin, “An Excluded Russia? – Not for Asia – Anthropocene Wars 6”, The Red Team Analysis Society, 3 October 2022).
As it happens, the global agricultural tensions that the fertilizer production and trade disruptions induce may very well worsen in 2023, because of the emergence of a massive El Niño climate risk.
A Super El Niño and the overheating of geopolitics?
During an El Niño event, the equatorial Pacific Ocean may heat up to 3°, thus heating up the whole atmosphere. The singular aspect of the 2023-2024 El Niño is that it happens in a time of rapidly intensifying climate change. The atmosphere temperature being already 1.2° above the mid-18th century pre-industrial level, the El Niño peak temperature may very well temporarily heighten the atmosphere’s heat at 1.5°. As it happens, this level is nothing but the upper peak limit of what climate scientists establish as the upper climate security limit (Kate Abnett, “World could face record temperatures in 2023 as El Niño returns”, Reuters, April 20, 2023 and Ajit Niranjan, “How climate change affect El Niño and La Nina cycles?”, DW, 01/27/2023).
Indeed, El Niño has a direct impact on South America climate regions. For example, throughout centuries, El Niño’s events have strong impacts in South America’s North-East, especially in Brazil by triggering prolonged droughts (Paloma Trascasa-Castro, “Four Possible Consequences of the El Niño Return in 2023”, The Conversation, 26 January 2023).
This could turn into a massive geopolitical problem, because of the heightening agriculture exports from Brazil to China. Those exports have exploded since 2018, when Beijing decreased trade taxes on Brazilian products. This decision was made in order to compensate for the decrease in U.S. products’ imports, in response to the trade war that the Trump administration was initiating and that the Biden administration is carrying on, while tensions heighten with China about the Taiwan issue (Tripti Lahiri, “Did Biden just end U.S strategic ambiguity on Taiwan?”, Quartz, 23 May, 2022, and Jean-Michel Valantin, “The US Economy, Between the Climate Hammer and the Trade war Anvil – The US Soybean Crop case”, The Red (Team) Analysis Society, October 8, 2018).
Lula strikes back
It is in this context that Lula da Silva, the newly re-elected president of Brazil, visited Xi Jinping, the President of the People’s Republic of China, in order to keep on deepening the trade ties between Brazil and China (Cede Silva, “Lula and Xi sign 15 agreements on trade, agriculture, new satellite”, The Brazilian Report, April 14, 2023).
Those ties are already quite dense, given the growth of Chinese soybean imports. Indeed, 80% of the Chinese soybean imports are from Brazil, which represents 54,39 million tons, and from the United States, which represent 29,5 million tons (Genevieve Donnellon-May and Felipe Porto, “Brazilian soybeans and China’s food security”, The Strategist, 21 April 2023).
88% of the Chinese soybean imports are used for animal feed and especially pig feed, the Chinese pig population representing half of the world pig population. The pork industry answers to the Chinese growing urban domestic demand for meat (Jean-Michel Valantin, “China, The African Swine Fever Pandemics and Geopolitics”, The Red Team Analysis Society, October 14, 2019).
As China is 1.4 billion strong, it needs to access immense and worldwide resources pools a matter of food security. So, for the Middle Kingdom, importing Brazilian agriculture products is a matter of social cohesion. Reciprocally, from the Brazilian perspective, deepening ties with China is, among other matters, a way to guarantee to Brazilian farmers the imports of the fertilizers they need for the Brazilian agricultural development (Donnellon-May and Porto, ibid).
Knowing that the war in Ukraine and the 2022 succession of climate shocks led to a tightening of the global fertilizer market, this Brazilian initiative appears as a way to secure its own economic development, while supporting the Chinese food security. It is in this context that President Xi and President Lula announced that the USD 150 billion in contracts would be paid in yuan. Thus the Brazilian-Chinese contracts reinforce the progressive trend towards the monetary diversification of the emerging multipolar world, and its relative dedollarization (Allsa Rosales, Alejandro Ducancarrete, “Brazil-China Strategic Partnership”, S&P Global Market Intelligence Blog, April 06, 2023).
El Niño, a potential driver of geopolitical destabilization
However, the 2023-24 El Niño may very well endanger these contracts, thus the Chinese food security. As we have seen, Brazil is particularly vulnerable to El Niño events. If the 2023-24 event is as violent as some weather centres warn about, there is a high risk that it will hinder the Brazilian crop yields, thus making it difficult to answer China’s demands (G. Kay et al., “Assessing the chances of unprecedented dry conditions over North Brazil during El Niño events”, IOP Science Environmental Research Letters, 19 May, 2022). This already complex situation may very well be complicated by the state of the global supply of fertilizers, that are heavily dependent on fossil fuel prices (“Brazil’s Lula calls for end to dollar trade dominance”, Modern Diplomacy, April 15, 2023)
One must factor in this potential Brazilian difficulty with the heightening vulnerability of China to climate change (Genevieve Donnellon-May, “How climate change is shaping China’s domestic security choices“, The Strategist, 18 April 2023, and Hendrik J. Bruins and Fengxian Bu, « Food Security in China and Contingency Planning : the Significance of Grain Reserves », Journal of Contengencies and Crisis Planning, September 2006 and Erin Sikorsky, China’s Climate Security Vulnerabilities, Centre for Climate and Security, Council on Strategic Crisis, 2022). This continental country experiences the consequences of a growing number of regional scale extreme weather events, such as giant floods, droughts and heatwaves that hammer its agriculture sector, thus its food security (Ibid.).
One must remember that the war in Ukraine triggers a massive disruptions of the European gas adduction from Russia. Thus, Europe needs to access to new resources bases on an already tight market. The problem is that, because of the growing Asian gas consumption, gas prices remain at a high levels.
El Niño may turn this situation into an ugly international competition if, as certain meteorology centres forewarn, it worsens the 2023-24 European winter (Trascasa-Castro, ibid). In that case, European countries will need to import more gas, and that will intensify pressure on prices, thus on the use of gas by agriculture.
Geopolitics and the return of Maslow’s hierarchy of needs
The Great Driver
Thus, the self-reinforcing interactions between the war in Ukraine, the worldwide agricultural tensions, rapidly changing geopolitical conditions and climate change create a nexus that is a major driver of geopolitics. From this nexus emerges a potential reinforcement of food insecurity crisis that started around 2021, while being turbo-charged by the war in Ukraine and, very possibly, by El Niño in 2023.
To care or not to care about people, that is the danger !!!
Knowing that, historically, food crises have the potential for being major drivers of social and political upheaval in already destabilized countries or continental regions, one may wonder if the years 2023-2024 are going to be years of major upheavals and regime change. As Geoffrey Parker, in its magisterial book Global Crisis, War, Climate change and Catastrophe in the Seventeenth Century, (Yale, University Press, 2013) notes, during the “little ice age” of the 17th century, numerous regimes were victims of the convergence of famines induced by harsh winters and cold winters, bad management of catastrophes, and multiplication of revolts against governments that extract taxes while being unable to feed and take care of their people.
One can only wonder if this model may not become quite active during the coming El Niño period, because climate change is going to interact with the numerous agricultural, economic and geopolitical vulnerabilities that define our current period.
In other terms, the question arises of the risks and probabilities of a convergence of civil hunger wars with international geopolitical upheavals, on a global scale.
In the late winter of 2022-2023, artificial intelligence (AI) made again the buzz. This time, it is not the amazing capacity an artificial intelligence agent, Alphago by DeepMind (now Alphabet/Google), demonstrated to win alone against a go Master, but the ability to discuss and do “many things as a human” displayed by the latest version of OpenAI (Microsoft) AI model, GPT-4.
As each time disruptive technology spreads, we may complain, struggle against it, or fear it. Yet, it is highly probable (over 80%, although not certain) that AI and more specifically the “GPT-type” of AI, will generate significant changes.*
The wisest behaviour when facing such wild changes is to find out how we can make sure the technology remains a tool to serve us rather than becoming slave to or victim of the technology.
This series of articles will thus explore concretely how AI and more specifically those AI based on GPT-like-models can help us anticipating the future, notably in the fields of geopolitics, national and international security.
The first article of the series first presents what are GPT models, ChatGPT and why they matter in terms of occupation and jobs. Then, we test ChatGPT on a specific question: “the future of the war in Ukraine over the next twelve months”.
After an initial disappointment we explain, we proceeded with the test to determine if ChatGPT can assist us in identifying variables and their causal relationships for strategic foresight and early warning analysis. We provide a transcript of our conversation with ChatGPT along with our comments, and conclude that there is sufficient potential to create an AI assistant for variables named Calvin (please visit the link).
ChatGPT, GPT, Generative AI… Let’s get things right first
Why does it matter?
On 5 and 7 April 2023 Goldman Sachs in its Insights and in the special tech edition of its Briefings warned about the “sweeping changes to the global economy” that “Generative Artificial Intelligence” (see below) would bring.
“They could drive a 7% (or almost $7 trillion) increase in global GDP and lift productivity growth by 1.5 percentage points over a 10-year period…”
However, “Shifts in workflows triggered by these advances could expose the equivalent of 300 million full-time jobs to automation…”
OpenAI, for its part, also carried out research on the impact on the labor market of its AI models and more generally of Large Language Models (LLMs) (Tyna Eloundou, Sam Manning, Pamela Mishkin, Daniel Rock, “GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models“, ArXiv, 17 Mar 2023 (v1), last revised 23 Mar 2023 – v4). Note, however, that OpenAI also has a corporate and legal interest in promoting LLMs and more particularly its GPTs-models as “general purpose technology.” For OpenAI, to see its GPTs-models perceived as “general purpose technology” would, for example, imply a very strong advantage in the protection of its trademark and in preventing others to use the name GPT (e.g. Connie Loizos, “‘GPT’ may be trademarked soon if OpenAI has its way“, TechCrunch, 25 April 2023).
In general, OpenAI Research found that:
“… around 80% of the U.S. workforce could have at least 10% of their work tasks affected by the introduction of LLMs, while approximately 19% of workers may see at least 50% of their tasks impacted…
Our analysis suggests that, with access to an LLM, about 15% of all worker tasks in the US could be completed significantly faster at the same level of quality. When incorporating software and tooling built on top of LLMs, this share increases to between 47 and 56% of all tasks.”
Generative AI is meant to particularly impact “software, healthcare and financial services industries”, and, more largely, the media and “entertainment, education, medicine and IT industry” sectors (Ibid., Goldman Sachs Insights, “Stability AI CEO says AI will prove more disruptive than the pandemic“, 31 March 2023).
In general, it is estimated that 900 types of occupations will be impacted, and first among them knowledge workers, scientists, and software coders (Ibid.).
As human beings concerned with the future, or more specifically as scientists and practitioners of strategic foresight and early warning, we need thrice to consider these developments.
First, because, being concerned with the future, we must be able to input the development and use of AI into all our foresight and warning analysis. This is why, for example, we created our initial series of articles on AI.
Second, practitioners of strategic foresight, early warning, risk management etc. are “knowledge workers” and “scientists.” We are thus on the front line of those who will be hit by Generative AI, if Goldman Sachs is right. Hence it is better to make sure AI serves us rather than kill us.
Finally, and more idealistically, if Generative AI indeed helps easing the process of anticipation in many ways, then it should also help spreading widely the use of actionable foresight and early warning. As a result, obstacles to crisis prevention and threat mitigation will be potentially reduced. However, challenges related to the organisation of the anticipation process and the willingness to heed warnings may remain largely unaffected.
What are ChatGPT, GPT-based AI and Generative Artificial Intelligence
GPT-models
GPT is a language model (Natural Language developed by OpenAI (Microsoft) that uses deep learning to generate human-like responses to prompts. The “GPT” stands for “Generative Pre-trained Transformer,” which means that the AI has been trained on vast amounts of text data to understand the nuances not only of the English language but also of other languages. GPT-models are part of the Generative AI family.
The newest model still tested by OpenAI is gpt-4. The most recent model OpenAI commercialises for usage is gpt-3.5-turbo. Waiting for gpt-4 to be available, gpt-3.5-turbo is the model we use here at RTAS for our experiment with AI assistants for Strategic Foresight and Warning: Aria (always available throughout the website, bottom right-hand corner), Calvin, Kai, Regina and Pithia.
ChatGPT
ChatGPT is an application using a GPT model that can hold a conversation with a human and generate responses that sound like they were written by a person. This is what sets the application apart and also frightens people. In March-May 2023, the public version of ChatGPT uses the model gpt-3.5-turbo. The most advanced application uses the newest model gpt-4, but is only available to paying subscribers (via ChatGPT Plus). For external usage through API, developers and users must apply through a waiting list.
Generative AI is thus typically based on deep learning models, which are trained on large datasets of examples in order to learn patterns and generate new content. We have, for example, generative adversarial networks (GANs – Ian Goodfellow et al. “Generative Adversarial Networks“, 2014) and variational autoencoders (VAEs – defined in 2013 by Kingma et al. and Rezende et al. – for an explanation J. Altosaar, “Tutorial – What is a variational autoencoder?“). For instance, a GAN might be trained on a dataset of images, and then used to generate new images that are similar in style and content to the original dataset, but are not exact copies.
Generative AI is thus a type of AI that is designed to create or generate new and original content, such as images, videos, music, or text. You can see below examples of images generated with OpenAI Dall-E model for this article, on three topics: deep sea security, space security and steampunk architecture.
Images for Deep Sea Security, Space Security, Steampunk architecture – Images generated by Generative AI (Dall-e-2 model 25 April 2023)
Usage, applications and impacts
Generative AI has a wide range of potential applications, from creating realistic 3D models to generating personalised content for users. However, it also raises ethical and security concerns around the potential misuse of generated content, such as deepfakes or fake news.
The world into which an application such as ChatGPT actually evolves, as well as most GPT-based applications is digital. In other words, most GPT-based apps have no capability to act directly concretely in reality… except if human beings become their actuators (see Helene Lavoix, “Actuator for AI (1): Inserting Artificial Intelligence in Reality“, The Red Team Analysis Society, 14 January 2019).
Thus, those activities that will be most impacted by GPT-based applications and their likes are those located within the digital world. Actually, we may rephrase this as: the more insubstantial – in the meaning of not having physical existence – our activity, the more likely it will be impacted by Generative AI applications such as GPT-based apps.
For example, if you are a plumber or a mason, it is highly unlikely ChatGPT or similar GPT-based application will make a serious impact on your activity. It may help people understanding drains or masonry, and give them advice and steps to follow to do something, but the real activity of repairing a basin or removing a part of a wall to make a cupboard will still be made by a real human being and likely by a specialist.
On the contrary if your work is directly related to and carried out in the world-wide-web from web-marketing to coder and developer, your work is very likely to be heavily impacted by ChatGPT or its likes.
In the world of activities related to ideas, including knowledge, similarly, the impact of Generative AI will highly likely be important.
…information processing industries (4-digit NAICS) exhibit high exposure, while manufacturing, agriculture, and mining demonstrate lower exposure [to LLMs and GPTs].
“Occupations with the highest exposure to GPTs or GPT-powered software”, Eloundou, et al. (“GPTs are GPTs, 2023), Table 4, p.16
Indeed, OpenAI’s research paper presents a table of impacted occupations, as reproduced here.
Logically, it appears that there are also variations in the degree of exposure of “ideational” activities according to the types of skills most necessary for an activity. Science and critical thinking are the least exposed and impacted by LLMs, whilst programming and writing are part of the most exposed activities:
“Our findings indicate that the importance of science and critical thinking skills are strongly negatively associated with exposure, suggesting that occupations requiring these skills are less likely to be impacted by current LLMs. Conversely, programming and writing skills show a strong positive association with exposure, implying that occupations involving these skills are more susceptible to being influenced by LLMs.”
“Skills exposure to GPTs or GPT-powered software”, Eloundou, et al. (“GPTs are GPTs, 2023), Table 5, p.17
Eloundou, et al. (“GPTs are GPTs, 2023) provide a table, reproduced here, estimating the exposure of various types of mainly cognitive skills.
This will allow each of us to appraise which of our tasks can be eased by GPT-like models, or threatened by them, according to the way AI is perceived, integrated within society and used.
Our concern with the use of GPT-based applications for strategic foresight and warning is thus a case of a larger issue regarding the way Generative AI will impact knowledge and ideas-based activities.
Now, concretely, the type and extent of impact of Generative AI models and their applications will depend upon the specifics of each model and its applications in regard to specific activities. Let us thus turn practically to such a case, the use of ChatGPT for strategic foresight and warning, and the first test we did, focused on the future of the war in Ukraine.
Testing ChatGPT on the future of the war in Ukraine
Not (yet) a tool to monitor current events
The first challenge we faced was that gpt-3.5-turbo, thus the model used by ChatGPT, ended its training in September 2021. The second was that ChatGPT is a closed system, unable to access the internet or any source of information after the end of its training.
In the words of ChatGPT, asked if it could give a political assessment on current events:
I can provide political assessments on current events to the best of my abilities based on the information available up until my last training cutoff in September 2021. However, please keep in mind that my responses might not reflect the most up-to-date developments or the current state of affairs, as the world is constantly evolving.
ChatGPT – 2 May 2023
Hence, ChatGPT and its likes cannot be used, for now, for all the steps of the strategic foresight and early warning process or risk management system that need up to date information. For example, it cannot be used for monitoring and surveilling early warning issues, nor to estimate the likelihood of scenarios or use the latter to steer policy. In terms of horizon scanning, it would need to be completed by other tools.
For those who would be disappointed, please note that OpenAI has opened its models to developers working on plugins for ChatGPT that would, for example, allow to “retrieve real-time information”. It is thus a question of time before GPT-based models and applications can be up-to-date. Indeed, the “New Bing“, Microsoft new search engine, uses GPT-4 and, de facto, accesses the world-wide-web.
Even though developments are very fast in the field, for now, our test will be done with what is available: a Generative AI which “knowledge” was cut off in September 2021.
If ChatGPT, as it is currently (Spring 2023) is not a tool we can use to monitor current evolutions, does that also mean it is useless for our purpose? Alternatively, even cut off from most recent events and knowledge, can it nonetheless be useful?
First milestones for a tool contributing to build a model for strategic foresight and early warning
Considering the methodology of strategic foresight and early warning, we shall test in which way ChatGPT and GPT-models can become tools for different aspects and parts of the analytical process.
Knowing that most serious methodologies of strategic foresight and warning, indeed any analysis, are grounded in explicit modeling, we shall examine first the capability of ChatGPT to help us with the creation and development of our model (see Hélène Lavoix, “Modeling for Dynamic Risks and Uncertainties (1) : Mapping Risk and Uncertainty“, The Red Team Analysis Society, 2018 [2011]; Joshua Epstein, Joshua M., “Why Model?“, Journal of Artificial Societies and Social Simulation 11(4)12, 2008; The Millennium Project: Futures Research Methodology,Version 3.0, 2009).
Can ChatGPT assist in identifying the crucial factors and actors relevant to our question? More precisely, can it aid in discovering the variables and causal relationships that drive the dynamics of our strategic foresight and warning issue?
We cut and pasted the conversation with ChatGPT below, and added comments in the column next to the answers.
Dialogue with Chat GPT (26 March 2023)
Comments
Can you identify variables with their attributes for the issue ‘the future of the war in Ukraine over the next 12 months’?
ChatGPT:
Certainly! Here are some possible variables with their associated attributes that could be relevant for the issue of the future of the war in Ukraine over the next 12 months:
Military strength: The relative military strength of the opposing sides in the conflict, including their weaponry, training, and troop levels.
Diplomatic efforts: The extent and success of diplomatic efforts to resolve the conflict, including negotiations between Ukraine, Russia, and other relevant parties.
Economic sanctions: The use and effectiveness of economic sanctions against Russia, which has been accused of supporting separatist rebels in eastern Ukraine.
Domestic politics: The domestic political situations in Ukraine, Russia, and other relevant countries, including the popularity of leaders and their willingness to compromise or escalate the conflict.
International alliances: The level of support that Ukraine and Russia receive from their allies and partners, including NATO, the EU, and China.
Humanitarian situation: The humanitarian situation in Ukraine and the impact of the conflict on civilians, including displacement, casualties, and access to basic needs like food, water, and medical care.
Media coverage: The media coverage and public opinion on the conflict in Ukraine, both domestically and internationally, which can shape political decisions and public pressure for resolution.
These are just a few possible variables that could be relevant for understanding the future of the war in Ukraine over the next 12 months. Other factors, such as geography, historical context, and cultural differences, may also be important to consider.
Even though the GPT models were closed before the war started, a war is grounded in dynamics that often start long before the onset of the war. Furthermore, knowledge on international relations, war, the various actors involved etc. builds upon millenia of understanding. Hence a GPT training model stopped in September 2021 should be adequate to help us identifying variables and their causal relationships for our issue. We would only have to check that the variables identified allow for taking into account the real-life events and dynamics that took place after September 2021. If necessary, we could correct our model accordingly.
Here the variables given by ChatGPT are correct but, as stated by ChatGPT, not exhaustive, when we need not all but yet far more variables than what was given here by ChatGPT. Furthermore, we are still at a very high level of generality. The variables given are hardly sufficient to capture the intricacies of real dynamics, the specificities of each actor, etc. They do not either integrate aspects of knowledge and understanding such as the systemic level of analysis.
Thus, with the type of question used initially, ChatGPT answers could be helpful for beginners, lay people and non specialists starting an analysis on this type of issues. These variables can help as a starting point but are hardly sufficient.
In terms of the attributes of the variables, some are given but not systematically. This aspect will have to be handled more precisely and specifically later on.
Can you add variables relative to the international system
ChatGPT:
Certainly! Here are some additional variables related to the international system that could be relevant for the issue of the future of the war in Ukraine over the next 12 months:
Geopolitics: The broader geopolitical context of the conflict, including the power dynamics and strategic interests of the major powers involved, such as the US, Russia, China, and the EU.
International law: The role of international law and institutions in resolving the conflict, including the authority and enforcement capabilities of bodies like the UN and the International Criminal Court.
Norms and values: The role of shared norms and values, such as democracy, human rights, and the rule of law, in shaping international attitudes towards the conflict and influencing the behavior of the parties involved.
Economic interdependence: The degree of economic interdependence between Ukraine, Russia, and other relevant countries, and the potential impact of the conflict on trade, investment, and global economic stability.
Military alliances: The impact of military alliances and security arrangements, such as NATO and the Collective Security Treaty Organization, on the conflict and the potential for escalation.
International cooperation: The extent and effectiveness of international cooperation and coordination in addressing the conflict, including efforts to provide humanitarian aid, monitor ceasefire agreements, and support diplomatic negotiations.
These variables highlight the importance of understanding the broader international context in which the conflict is unfolding, and how it shapes the actions and decisions of the parties involved.
We thus asked ChatGPT to add other types of variables we knew to be important.
The results obtained were both interesting and good. It was particularly striking that ChatGPT thought about including norms and values.
However, again, variables are missing. For example, elements related to the Realist school of International relations, are not present, but we can expect that more precise prompts would yield better results. We should also be careful that biases are not introduced at the stage of the choice of variables.
After two exchanges, we could see a way to use ChatGPT for variables, through iterations between practitioner and IA, helping the former getting progressively the variables needed.
Should we also add the American national interest as variable?
ChatGPT:
Yes, the American national interest could be a relevant variable to consider in the issue of the future of the war in Ukraine over the next 12 months. The United States has been involved in the conflict in various ways, including providing military and economic aid to Ukraine, imposing sanctions on Russia, and supporting diplomatic efforts to resolve the conflict.
Some possible attributes of this variable could include:
Strategic interests: The extent to which the conflict in Ukraine aligns with or challenges American strategic interests, such as promoting democracy and human rights, containing Russian aggression, and maintaining stability in Europe.
Domestic politics: The role of domestic politics in shaping American policy towards the conflict, including the views and interests of key stakeholders such as Congress, the President, and interest groups.
Alliances and partnerships: The impact of American alliances and partnerships, such as NATO and the EU, on the conflict and the potential for escalation.
Economic interests: The potential impact of the conflict on American economic interests, such as trade and investment with Ukraine and other countries in the region.
Military capabilities: The extent to which American military capabilities could be mobilized in response to the conflict, including the potential for direct military intervention or support for Ukrainian forces.
However, it’s important to note that the American national interest is just one of many variables that could be relevant to understanding the future of the war in Ukraine over the next 12 months, and it should be considered in conjunction with other factors, such as the interests and actions of other key actors in the conflict.
We further tested ChatGPT by asking if a very specific variable, in that case “the American National Interest” was a variable for our question.
The answer was interesting even though flawed from the strict point of view of the definition of a variable and its attributes in social science.
In social science terms, “a variable is a logical set of attributes” (art “Variable and attribute (research)” Wikipedia – using Earl R. Babbie, The Practice of Social Research, 12th edition, Wadsworth Publishing, 2009, p. 14-18).
It appears that here our instructions to and definitions for ChatGPT were not clear enough. Thus the result was not what we expected.
Rather than obtaining a clear set of variables with their attributes, we obtained one variable with influencing (or dependent) and influenced (independent) variables, with explanations and attributes, all presented in an explanatory manner.
The substance of the answer, yet, let us expect that if we correct our question and, eventually, train ChatGPT adequately, then we could – hopefully – obtain the right set of variables with their clear attributes.
Now you highlighted variables can you specify causal links between them?
ChatGPT:
Certainly! Here are some possible causal links between the variables previously identified for the issue of the future of the war in Ukraine over the next 12 months:
Military strength -> Conflict escalation: If one side perceives a significant military advantage, they may be more likely to escalate the conflict, leading to increased violence and casualties.
Diplomatic efforts -> Conflict resolution: Successful diplomatic efforts could lead to a peaceful resolution of the conflict, potentially through negotiations or a ceasefire agreement.
Economic sanctions -> Political pressure: Economic sanctions could put political pressure on Russia to change its behavior, potentially leading to a reduction in support for separatist rebels and a de-escalation of the conflict.
Domestic politics -> Policy decisions: The political situations in Ukraine, Russia, and other relevant countries could influence the policy decisions of their leaders, potentially leading to either escalation or de-escalation of the conflict.
International alliances -> Military and economic support: The level of support that Ukraine and Russia receive from their allies and partners could influence the military and economic capabilities of the opposing sides, potentially leading to escalation or de-escalation of the conflict.
Humanitarian situation -> International intervention: The humanitarian situation in Ukraine could increase international pressure for intervention, potentially leading to a more forceful response to the conflict.
Media coverage -> Public opinion: The media coverage of the conflict could shape public opinion and political decisions, potentially leading to either escalation or de-escalation of the conflict.
Geopolitics -> Strategic decisions: The broader geopolitical context of the conflict could influence the strategic decisions of the major powers involved, potentially leading to either escalation or de-escalation of the conflict.
International law -> Compliance: The role of international law and institutions in resolving the conflict could influence the compliance of the parties involved with ceasefire agreements and other diplomatic efforts.
Economic interdependence -> Economic impact: The degree of economic interdependence between Ukraine, Russia, and other relevant countries could influence the potential economic impact of the conflict, potentially leading to pressure for de-escalation.
Military alliances -> Escalation risk: The impact of military alliances and security arrangements could increase the risk of escalation, potentially leading to more forceful responses to the conflict.
International cooperation -> Conflict resolution: International cooperation and coordination could support diplomatic efforts to resolve the conflict, potentially leading to a peaceful resolution of the conflict.
American national interest -> Policy decisions: The American national interest could influence the policy decisions of the US government towards the conflict, potentially leading to either escalation or de-escalation of the conflict.
It’s important to note that these are just some possible causal links between the variables, and the actual causal relationships between the variables may be more complex and interdependent than these simple relationships suggest.
Now we knew we could with corrections, training and iterations get variables for our model, the next step was to know if ChatGPT could identify causal relationships.
Interestingly, ChatGPT was able to gather all variables of our exchanges since the start of the conversation.
It could also identify some relationships among variables, but by no means all. To highlight just one missing relationship among many, “conflict escalation” and “escalation risk” are not linked by ChatGPT.
We may imagine, although we did not test it, that again, we could prompt ChatGPT into testing further the existence or not of other causal relationships. However, here using ChatGPT could prove heavier and longer than not using it and creating our causal relationships directly out of our understanding, out of classical build up of knowledge (search, reading, comprehending) and/or expert workshops.
Furthermore, an output listing causal relationships between variables could be extremely boring to read and hardly practical.
To build causal relationships between variables, it is best to use graph building and visualisation software and not linear-based text. ChatGPT being a text-based app., it cannot really help, or at least not directly here.
For the sake of completing the experiment we nonetheless went on, trying to find a way to translate easily ChatGPT output in something a graph software could read and use.
Now can you show the causal relationships between variables as a matrix?
ChatGPT:
Certainly! Here is a matrix that shows possible causal relationships between the variables identified for the issue of the future of the war in Ukraine over the next 12 months:
Causal Links
Military Strength
Diplomatic Efforts
Economic Sanctions
Domestic Politics
International Alliances
Humanitarian Situation
Media Coverage
Geopolitics
International Law
Economic Interdependence
Military Alliances
International Cooperation
American National Interest
Military Strength -> Conflict escalation
1
Diplomatic Efforts -> Conflict resolution
1
Economic Sanctions -> Political pressure
1
Domestic Politics -> Policy decisions
1
International Alliances -> Military and economic support
1
Humanitarian Situation -> International intervention
1
Media Coverage -> Public opinion
1
Geopolitics -> Strategic decisions
1
International Law -> Compliance
1
Economic Interdependence -> Economic impact
1
Military Alliances -> Escalation risk
1
International Cooperation -> Conflict resolution
1
1
American National Interest -> Policy decisions
1
1
1
1
1
1
In the above matrix, the row variable represents the cause or independent variable, and the column variable represents the effect or dependent variable. An “X” in a cell indicates a potential causal link between the corresponding row and column variables, and an empty cell indicates no significant causal link.
Again, it’s important to note that these are just some possible causal links between the variables, and the actual causal relationships between the variables may be more complex and interdependent than these simple relationships suggest.
Because the mathematical tool behind a graph is a square matrix, we asked ChatGPT to translate the causal relationships for the variables it identified as a matrix.
The result was disappointing, yet also exciting.
Exciting because it indeed created a matrix, disappointing because the relationships ChatGPT had found initially were included within the variables of the rows, and the links, as a result, were not right.
However, with training of the GPT model and effort, it may be possible to obtain something better… to be tested in the future.
We could then export the matrix as a csv. file and read it in Gephi as a graph.
Conclusion of the test
As it is, ChatGPT and gpt-3.5-turbo model cannot directly output a good enough model for a strategic foresight and early warning’s question on an issue pertaining to national and international security.
For this purpose, there is however a great potential in GPT and its apps, and thus probably in Generative AI.
As it is, we estimate that ChatGPT can be nonetheless very helpful to beginners and non-specialists. Iterations and asking increasingly more precise questions appear as the best systematic way to use ChatGPT for variables and causal relationships. We may also imagine the AI can help specialists if the questions asked are precisely formulated – and thus well understood by ChatGPT.
This also highlights the key importance of prompts (the questions asked to a Generative AI) when interacting with such AIs, and suggests thus a new type of activity that may emerge alongside traditional ones, for strategic foresight and warning in particular and more generally for good usage of generative AI.
We also identified other challenges impacting the identification of variables and causal relationships, such as the problem of bibliographic references, which are lacking here in ChatGPT answers. Indeed, variables and causal relationships should be grounded in facts, logic, as well as scientific research. Thus, ideally, we would need a reference for each variable and each relationship. We shall deal with this key aspect in another article. Indeed, if erroneous or plainly fake variables and links were included in models, or if variables were omitted either willingly or because o biases, then the model would become useless, or biased, with severe consequences in terms of prevention.
As a whole, we estimate that there is enough potential here to create a corresponding AI Assistant, Calvin, that our members and readers will be able to use. We intend to continue improving this AI assistant. Notably, in the future, further training of the AI for our specific purpose – called fine-tuning – could yield very interesting results. However, it seems best to wait until the full release of GPT-4 to start such a process, after carrying out a full test again with GPT-4.
Finally, assuming a Generative AI could indeed create the conceptual models we need, then one potential danger would be that practitioners would stop making the effort to think (see also ** below). We may wonder if this would lead to a decrease in cognitive capacities. In that case, it would be important to make sure that thinking continues being exerted, and that the capacities of Generative AI are properly embedded into a process that does not harm human beings.
On the positive side, the use of Generative AI could so much increase the speed of creation of a proper model that it would ease and spread the use of proper strategic foresight and warning and as a result enhance human capacities to prevent threats.
Notes
*… unless other even more upsetting events take place. The specifics of the changes that will emerge from the use of AI in general, ChatGPT-like AI in particular, may also differ from our current expectations. These two points will be addressed in future articles. Here we concentrate on the highly probable and the evolution generated by ChatGPT-like AI.
**… this task is also used in workshops to open-up the minds of participants, to generate new ideas. For analysts, the very fact to make the cognitive effort to find out variables and their causal relationships enhance understanding and comprehension of an issue. Thus, being able to carry out this task alone or in a group has great value in itself. To see it being completely done by an AI-agent would is thus likely to have serious negative consequences. It will thus be key to creatively integrate the AI tool, once operational, in a way that minimise drawbacks.
Personal International Trainer to Hasten Intelligent Anticipation
To assist you in discovering and exploring strategic foresight and early warning for proactive anticipation and prevention.
This GPT-based AI helps you here with concerns and uncertainty about the future by presenting possible scenarios. Explore too cascading impacts.
This page is tailored to individuals who discover the use of scenarios for proactive anticipation and prevention, which is referred to as actionable strategic foresight and warning.
Click on the AI assistant to access the AI-powered interacting form directly. Please note that OpenAI GPT models used for the AIs are currently NOT able to browse the Internet.
With the help of the AI-powered form below, first, specify further your future concerns. Then, request scenarios. Optionally, generate an image for your scenarios.
This is an introduction to scenarios, as well as an experimental approach to AI and, for now, GPT-based models and architectures. The scenarios the AI provides here, at this stage, are merely examples and not a structured set for probabilistic analysis, action design, and policy implementation. Furthermore note that GPT-based AI is also prone to confabulation, which is truly useful for scenarios yet, do not hesitate to check things out.
Tips: * Check how to maximise interactions with AI. * Try! The first 7 queries (across all our AI assistants) are complimentary. For guests: in a form (Pithia), one click on submit [red button] = 1 query – In a chat (Aria, Calvin, Kai, Regina, Sphinx), 1 question and 1 answer = 2 queries.
Define your concern and transform it in a strategic foresight and early warning question.
Tips: If you want the AI to create another question with the same parameters, click again the button above. Be careful, previous questions will be lost once you hit the button again. Thus, don’t forget to cut and paste the question somewhere before to try something different. No undo…!
Start planning ahead
Get scenarios for your question
(These are samples of scenariosand not – yet – a truly valid set of scenarios)
Tips: You can demand as many new scenarios and narratives you want by clicking again on the button above. However, scenarios will not be saved. Thus, don’t forget to cut and paste them somewhere before to hit the button again.
Make your scenarios vivid
Tips: It is important to illustrate scenarios to make them more vivid (read Scenarios: Improving the Impact of Foresight thanks to Biases). AI-generated images are currently more fun than truly useful. They are not as meaningful and impacting as real art directed work. Contact our own art director for tailor-made artwork. AI generated images are more expensive than text (approx. 4x more to get one image than the scenarios).
Do you want to progress further in handling the future?
Kai
To enhance your scenarios, such as providing more narrative details or creating catchy titles, utilise our AI assistant for scenarios called Kai.
Calvin
If you want to build a better and real model for your question, the fundamental basis for excellent and valid scenarios, if you need indicators, use our AI assistant for indicators and variable: Calvin.
Regina
If you need help and definitions with geopolitical and political science concepts, definitions etc., use our AI assistant for geopolitics: Regina.
A way to say good bye to the Weekly! Stay put, we are working on something new and exciting…
Scans and signals
Using horizon scanning, periodically, we can collect weak – and less weak – signals. The signals point to new, emerging, escalating or stabilising problems. As a result, they indicate how trends or dynamics evolved. This collection of signals, with or without comments, is called a scan.
Scans must be focused on a specific theme or issue. The breadth of the focus may vary according to needs. The periodicity of collection and publication will also vary according to needs and focus.
In the field of strategic foresight and warning, risk management and future studies, it is the job of good analysts to scan the horizon. As a result, they can perceive signals. Analysts then evaluate the strength of these signals according to specific risks and dynamics. Finally, they deliver their findings to users: the scan. These users can be other analysts, officers or decision-makers.
“Weak” signals, the strength of signals and their relevance
We call signals weak, because it is still difficult to discern them among a vast array of events. However, our biases often alter our capacity to measure the strength of the signal. As a result, the perception of strength will vary according to the awareness of the actor. At worst, biases may be so strong that they completely block the very identification of the signal.
Increasingly one may wonder about the relevance of the idea of ‘weak signals” in our world: if you take the reality of the MIT/Club of Rome 1973 foresight on the sustainability of our world, then, can we truly still dare to say it is a weak signal regarding the impending – already present – global disaster in terms of sustainability? In 1973 it was a weak signal, but now? As so many do not truly pay attention beyond greenwashing, endless meetings and inefficient measures compared to what would be needed, as real awareness generating action is obviously not there, as a result, do the dire warnings still qualify as weak signal? How strong does a signal need to become to be taken into account as signal or even better warning? Part of the answer may be in the idea of timeliness, but if nobody wants to act, does timeliness also become obsolete?
Since 2011, we had been running a weekly scan that was published complimentarily on the Red Team Analysis Website. Its focus was political and geopolitical risks or, more largely, conventional and unconventional national and international security.
It was initiated as an experiment in crowdsourcing using social networks, mainly Twitter and sometimes Facebook. To avoid information overload, we chose a weekly rather than daily scan. The experiment being conclusive we went on publishing the scan.
However, Paper.li, the platform we used to create the weekly scan stopped using all sources on 6 April 2023 and definitely closed down on 20 April 2023. Alternatives are not suitable for open access and complimentary scans.
As archives are not kept by paper.li either, we chose to delete all related posts that did not include any content beyond the scan itself, and to redirect readers here.
Featured image: Image of the Swedish-ESO 15m Submillimeter Telescope (SEST) at ESO’s La Silla Observatory, located on the outskirts of the Chilean Atacama Desert, 600 km north of Santiago de Chile and at an altitude of 2400 metres. The photo was taken by Stefan Seip, one of the ESO Photo Ambassadors.
On 10 April 2022, six Chinese military heavy duty transport aircraft landed at Belgrade airport in Serbia. They were delivering the Chinese FK 3 export version of the HQ-22 surface-to-air weapons systems. This delivery deepens military ties between China and Serbia, following the delivery of 14 CH-92 combat drones in 2020 (Dusan Stojanovic, “China makes semi-secret delivery of missiles to Serbia”, AP News, April 10, 2022 and Sebastien Roblin, “Missile-armed Chinese drones arrive in Europe, as Serbia seeks Airpower edge”, Forbes, July 9 2020).
As it happens, starting in 2020, Serbia had been going through a very difficult period facing the Covid-19 pandemic. In these dire times, Beijing helped Serbia by providing masks, sanitary and genome sequencing equipment ( Jean-Michel Valantin, “China, “The Health Silk Road” of vaccines and Security”, The Red Team Analysis Society, February 15, 2021, and Hamdi Firat Buyuk, Danijel Kovacevic, Edit Inotal and Milica Stojanovic, “Turkey, Serbia, Bosnia, Hungary put trust in Russian, Chinese vaccines”, Balkan Insight, January 22, 2021).
Meanwhile, Beijing involved Serbia, Montenegro, Macedonia and Greece in its Belt & Road Initiative. This involvement takes the form of the reconstruction of the Serbian network of motorways, bridges and railways. It also includes the construction of a railway that runs from Athens and the port of Piraeus to Belgrade. From there, it connects to the railway to Hungary (Silvia Amaro, “China bought most of Greece’s main port and now it wants to make it the biggest in Europe”, CNBC, November 15, 2019).
There is thus a developing convergence between the Serbian economic, military and AI strategies and the Chinese presence in the Balkans, i.e. in Southern Europe.
We shall see what the strategic orientation of the Serbian development reveals about the European and NATO dimensions of the Chinese grand strategy in Europe. This analysis will lead us to unveil the Chinese “Northern/Southern European strategy” on a warming planet.
China comes to Serbia
While the war in Ukraine has been raging since 24 February, on 10 April 2022, six Chinese heavy duty military planes fly in formation above Greece and Macedonia. Then, in a not very discreet way, they landed in Serbia, delivering HQ-22 surface-to-air missiles systems (Jovan Knezevic, “Serbia : the first and only operator of Chinese drones and missiles in Europe”, IARI Istituto Analisi Relatione Internazionali, 31 January, 2023).
The weight of history
From the Serbian strategic point of view, this delivery enlarges the military cooperation with China. This cooperation started in 2020 with the delivery of 9 “Pterodactyl 1″combat drones (Jovan Knezevic, ibid).
From the Chinese point of view, one could assume that the installation of the HQ-22 in Serbia is imbued with an even more powerful political and geopolitical content.
Indeed, one must remember that, on 7 May 1999, a U.S Air Force B-2 stealth bomber launched 5 guided bombs on the Chinese embassy in Belgrade, killing three journalists. This happened during the NATO bombing campaign against Serbia.
That campaign was waged by NATO in order to force the Serbian government to evacuate its forces out of Kosovo, accusing the actions of Serbian forces of being a security risk in the region and accusing Serbia of an active campaign of ethnic cleansing in Kosovo (David Kilcullen, The Dragons and the Snakes, How the Rest Learned to fight the West, Hurst, 2020)
NATO and the U.S. declared that this strike was nothing more than a mistake due to poor preparation. However, the political authorities in Beijing denounced the act as a deliberate “barbaric attack and a gross violation of Chinese sovereignty”.
Hence, the 2022 installation of the Chinese HQ-22 in Serbia may be seen as a strategic answer to the NATO/U.S. “gross violation of Chinese sovereignty”. Equipping Serbia with powerful means of conventional deterrence against air attacks in the heart of southern Europe appears to be a strong signal of Chinese strategic assertiveness in the face of American influence.
This hypothesis is reinforced by the presence of numerous U.S. military bases in neighbouring Kosovo, Romania, Bulgaria, Greece and Germany (“List of countries with overseas U.S. military bases”, Wikipedia).
It is also interesting to note that the bombed embassy is now a huge Chinese cultural centre. Since 2014, it also hosts an antenna of the Serbian Confucius centre. The centre develops an important partnership with the Belgrade University of Novi Sad. This Confucius centre, as all the others worldwide, aims at developing the teaching of Chinese language alongside Chinese cultural influence (Reid Standish, “China builds a New Symbol in the Balkans – at the Site of a NATO Bombing”, Radio Free Europe, October 04, 2022).
Huawei, Belgrade and the AI New Silk Road
This Serbia-China military and cultural cooperation deepens with the development of the cooperation between the Chinese tech and AI giant Huawei and the Serbian Ministry of Interior (MOI). Since 2019, the MOI experiments with the installation of a network of surveillance captors in Belgrade, in order to further security. Furthermore, this cooperation also takes place in a couple of “Kosovar communities that are partly outside Pristina’s control”, which implies strong political tensions (Mila Djurdjevic, Sandra Cvetkovic, Andy Heil, “Serbia’s back-door bid to embed Chinese snooping tools in Kosovo”, Radio Free Europe, January 8, 2022).
At the same time, in 2020 Huawei signed a larger partnership with the Serbian government. It allows the Chinese firm to become the first commercial user of the state-owned data centre of Kragujevac. This partnership became the first Huawei digitalization centre. According to Huawei, the centre dedicates itself to the support of IT education and development of Serbia (Radomir ralev, “Huawei to use capacity at Kragujevac data centre”, SeeNews Business Intelligence for Southern Europe, Dec 09, 2020).
One has to observe that it is in this context and timeline that, in 2020, the Serbian government published its Strategy for the Development Artificial Intelligence in the Republic of Serbia 2020-2025 (Ibid, see also Hélène Lavoix, “Portal to AI-Understanding AI and Foreseeing the AI powered world”, The Red Team Analysis Society).
“The Strategy is in line with the European Artificial Intelligence Initiative, which sets out the European Commission’s artificial intelligence policy. In this context, the Republic of Serbia, as a candidate for EU membership, but also as a participant in the European Union Framework Program for Research and Innovation, seeks to provide the necessary extent of compliance with the European Union, which will enable full integration into the European Research Area and closer cooperation.”
Furthermore, in September 2020 President Alexandre Vucic, alongside with Avdullah Oti, the Kosovar Prime Minister, met President Donald Trump. Together, they ratified the “Washington Agreement”. However, this agreement refrains its signatories to install 5G infrastructure from “untrusted vendors”.
However, one must observe that, de facto, there are already multiple layers of Serbia-China technology cooperation. Thus, this cooperation is laying the ground for an amplification of the technological and AI cooperation between the two countries.
This trend became even stronger during the high tide of the Covid-19 pandemic. In these very difficult times, in 2021, Serbia, as many other countries, received sanitary masks, medical material and Sinovac doses from China. It was thus part of the Chinese “Health Silk Road” (Jean-Michel Valantin, “China, The Health Silk Road and Security”, The Red Team Analysis Society, February 15, 2021).
It is also in the context of the pandemic that, in 2021, the Beijing Genomics Institute expanded its operation in Serbia. That was the opportunity for creating a genome sequencing centre in Belgrade by donating the necessary equipment to the Molecular Genetics and Genetic Engineering of Serbia (“China’s biotechnology helps Serbia fight Pandemic, make scientific progress : Serbian expert”, Xinhua.net, 2021/09/13, “Genome sequencing center opens in Serbia, in cooperation with China”, Xinhua.net, 2021/12/13 and Mila Djurdjevic, “Under investigation abroad, Chinese gene giant expands in Serbia”, Radio Free Europe, December 30, 2022).
… To AI genomic power?
Genome sequencing plays a central role in the struggle against the Covid-19. It allows medical authorities to identify what type of variant circulates, as well as its level of dangerousness. Thus, it allows political authorities to devise policies as adapted as possible to the level of circulation of the virus. As a result, despite its economic difficulties, Serbia was able, thanks to Beijing, to protect its population as well as possible.
Hence, Serbia has, de facto, the means to develop the hybridation of genome sequencing with artificial intelligence. This a field of fundamental research and research and development. The convergence of AI and genomics has mammoth potentials in terms, among others, of predictive medicine that strongly interests AI actors such as Huawei (“New Silk Routes Group and Huawei to develop AI for personalized cancer treatment”, AsiaBiz Today, January 21, 2021)
These biotechnology equipments as well as the development of AI have thus the potential to turn Serbia into a regional “fourth industrial revolution” power thanks to its cooperation with China. This is especially true thanks to Huawei, that is deeply committed in research and development in the field of AI and genomics (“Centre for 4IR Serbia Launched at Biotech Future in Belgrade”, Modern Diplomacy, October 20, 2022).
In the same time, Serbia is having its road and railways infrastructures renovated and expanded by Chinese companies. It also becomes a sub contractant for China since the Chinese take over of the unsafe and very polluting Smedrevo steel mill, which exports its production to China. Thus, it appears that Serbia is becoming a main hub for the Belt & Road initiative in Southern Europe (“Chinese owned steel Mill coats Serbian town in red dust, cancer spreads”, Reuters, November 9, 2021).
Reciprocally, it also means that this country acquires quite an important role in the framework of the Chinese grand strategy.
Encircling Europe and NATO
Indeed, from a Chinese point of view, Serbia is now a particularly “useful space”. If, from a Western point of view, developing the trade, military, sanitary, AI and biotechnological capabilities of Serbia for Chinappears as a strategy in itself, it also has another dimension, anchored in Chinese philosophical and strategic thought. (Valantin, “China and the New Silk Road: the Pakistani strategy”, The Red Team Analysis, May 18, 2015).
That dimension is grounded in an understanding of the spatial dimension of China, in the geographic sense. Space is not only conceived as a support to spread Chinese influence and power to the “outside”. It also allows the Middle Kingdom to “aspirate” what it needs from the “outside” to the “inside”. (Quynh Delaunay, Naissance de la Chine moderne, L’Empire du Milieu dans la globalisation, 2014).
This is why we qualify some spaces as being “useful” to the deployment of the Chinese strategy. It is also why each “useful space” is related, and “useful”, to other “useful spaces”. In the same dynamic, the different countries involved in the deployment of the Chinese strategy are “useful spaces” for China.
This philosophy of space and time as flows is the basic material of the Chinese strategic tradition. As Scott Boorman, Arthur Waldron and David Lai, among others, establish quite clearly, this tradition expresses itself especially well through the “Go game”.
This very ancient game emphasizes the importance not to control, but to master the space of the adversary (Arthur Waldron, “China’s Military Classics”, Joint Forces Quarterly, Spring 1994). The strategy is to “convert” that space into one’s own. To do so, one has to “surround and conquer” the pieces, i.e. the space of the adversary.
The strategy of useful spaces
In order to win the game, the main goal is to attack the strategy of the adversary and not “only” its space. This strategic philosophy suffuses some of the most important Chinese strategic works, such as Sun Zi’s The Art of War. It drove some of the major strategic developments during the twentieth century.
It is true, for example, of Mao’s “revolutionary warfare” against Japan and the nationalist military (Scott Boorman, ibid). As we have seen in The Red Team Analysis Society, it also drives the mammoth “Belt & Road initiative” (Jean-Michel Valantin, “China and the Belt and Road Initiative” section, The Red Team Analysis Society).
Hence, in this strategic context and tradition, the question arises of the “usefulness” of Serbia. This “usefulness” appears in the context of the worldwide deployment of Chinese influence (David Lai, ibid). In other words, how is Beijing elaborating “shih”, the strategic configuration of favorable circumstances by installing capabilities in Serbia as well as in Europe?
One must note that the recent and rapid developments of the Chinese presence in Serbia and in the Arctic follow the same timelines. In other terms, we hypothesise that Beijing plays a worldwide “Go game” at a planetary scale as well as at the European scale.
From the European point of view, the presence of China in the Arctic is particularly meaningful. As we have explained in The Red Team Analysis Society’s publications, and related conferences since 2014, the notably Russian, Chinese, Japanese, and Indian race towards the Arctic is driving the emergence of the continental Russo-Asian bloc.
The mammoth oil, gas, mineral and biological resources are becoming a giant economic attractor. Meanwhile, because of the effects of the Arctic warming, the Russian authorities open the “Northern Sea route”.
Surround and Conquer
This new sea lane follows the Siberian coast and connects the Bering Strait to Norway and the Northern Atlantic. Thus, it also connects the immense Chinese and Asian basins of economic development to Northern Europe and to the Atlantic. While the number of Chinese convoys using the Northern Sea route grows regularly, Beijing multiplies bilateral trade agreements with Norway, Finland, Sweden, Denmark and the Netherlands, consolidating its access to the European market through Northern Europe (Jean-Michel Valantin, “Arctic China (2), The Chinese Shaping of the North”, The Red Team AnalysisSociety, June 9, 2014).
This means that China uses its growing presence in the Arctic and in Northern and Southern Europe to increase its global influence. This happens through a subtle and multi-scale Go strategy of “surround and conquer”. This game extends from China to the Arctic and to Northern and Southern Europe and joins the multiple continental and maritime “useful spaces”.
So, while it becomes a “near Arctic nation” and a technological supporter of Serbia, China “surrounds” the whole European region (Jean-Michel Valantin, “Is the West Losing the Warming Arctic?”, The Red Team Analysis Society, December 7, 2020).
Encircling Europe
As it happens, the heightening Chinese presence in Serbia, the Balkans and Greece, “completes” the “encirclement” of Europe by the “useful Serbian hub” at its south, while developing the China’s presence in Northern Europe. In other words, Europe is “under siege”, while being largely ignorant of the conversion of multiple European spaces to Chinese technological and trade norms.
In fact, using the framework devised by Hélène Lavoix, at the level of the normative dimension of the developing war between the U.S. and China, Serbia and other European countries are adopting the Chinese technological norms (Hélène Lavoix, “The War between China and the U.S- The Normative Dimension”, The Red Team Analysis Society, July 4, 2022).
However, this happens in a region where NATO is heavily influential through the memberships of Bulgaria, Romania, North Macedonia, Montenegro, Albania, Greece, Türkiye and Italy.
By doing so, the convergence of the development strategies of China and of the Balkans states, especially Serbia, undermines the American influence in this historically strategic region.
GDPR, Privacy and Cookies
The Red Team Analysis Society uses cookies to ensure that we give you the best experience on our website. This includes cookies from third party social media websites if you visit a page which contains embedded content from social media. Such third party cookies may track your use of the Red Team Analysis Society website.
If you click on "Accept", you accept our policy, we'll assume that you are happy to receive all cookies on the Red Team Analysis Society website and this will close this notice. Accept AllGDPR and Cookie Policy
Privacy & Cookies Policy
Privacy Overview
This website uses cookies to improve your experience while you navigate through the website. Out of these, the cookies that are categorized as necessary are stored on your browser as they are essential for the working of basic functionalities of the website. We also use third-party cookies that help us analyze and understand how you use this website. These cookies will be stored in your browser only with your consent. You also have the option to opt-out of these cookies. But opting out of some of these cookies may affect your browsing experience.
Necessary cookies are absolutely essential for the website to function properly. This category only includes cookies that ensures basic functionalities and security features of the website. These cookies do not store any personal information.
Functional cookies help to perform certain functionalities like sharing the content of the website on social media platforms, collect feedbacks, and other third-party features.
Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.
Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics the number of visitors, bounce rate, traffic source, etc.
Advertisement cookies are used to provide visitors with relevant ads and marketing campaigns. These cookies track visitors across websites and collect information to provide customized ads.
Pithia assists you in exploring 1st, 2d and 3rd-order impacts
Input Primary Event:
ChatGPT:
