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 this AI-powered form below that allows you to explore some direct, second and third-order effects for an event or decision.
We trained and tested the AI many times, notably on three issues:
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!
Tips: Try it, the first 10 queries (across all our AI assistants) are complimentary. The bar below shows how much you have used in red and how much you can still use in black:
For guests: in a form (Pithia), one click on submit [red button] = 1 query – In a chat (Aria, Calvin, Kai, Regina), a question and an answer = 2 queries.
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
What about impacts further away?
Identify 4th to nth order effects
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 the potential to offer increased capabilities and advancements which may surprise us. The future will tell…
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)
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.
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:
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.
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.
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
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 (once it becomes widely available) 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).
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).
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 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.”
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 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 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.
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.
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.”
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.
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)
Can you identify variables with their attributes for the issue ‘the future of the war in Ukraine over the next 12 months’?
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
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?
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?
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?
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:
American National Interest
Military Strength -> Conflict escalation
Diplomatic Efforts -> Conflict resolution
Economic Sanctions -> Political pressure
Domestic Politics -> Policy decisions
International Alliances -> Military and economic support
Humanitarian Situation -> International intervention
Media Coverage -> Public opinion
Geopolitics -> Strategic decisions
International Law -> Compliance
Economic Interdependence -> Economic impact
Military Alliances -> Escalation risk
International Cooperation -> Conflict resolution
American National Interest -> Policy decisions
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.
*… 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: Try it, the first 10 queries (across all our AI assistants) are complimentary. The bar below shows how much you have used in red and how much you can still use in black:
For guests: in a form (Pithia), one click on submit [red button] = 1 query – In a chat (Aria, Calvin, Kai, Regina), a question and an 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?
To enhance your scenarios, such as providing more narrative details or creating catchy titles, utilise our AI assistant for scenarios called Kai.
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.
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.
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.
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.”
It is interesting to note that the Serbian government claims that its AI strategy is coherent with EU norms.
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).
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?
From Serbia to the encirclement of 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).
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.
This is the 30 March 2023 issue of our weekly scan for political and geopolitical risks or, more largely, conventional and unconventional national and international security (open access). Scroll down to access the scan.
As paper.li, the platform we use to create the weekly scan goes down on 20 April 2023, and as alternatives are either not suitable or paying platforms, we shall not continue providing a scan free of charge. Contact us for scans created specifically for your organisation.
Using horizon scanning, each week, we collect weak – and less weak – signals. These point to new, emerging, escalating or stabilising problems. As a result, they indicate how trends or dynamics evolve.
As every week, below the scan itself, we briefly explain what is horizon scanning and what are weak signals.
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.
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. These users can be other analysts, officers or decision-makers.
Each section of the scan focuses on signals related to a specific theme:
world (international politics and geopolitics);
science including AI, QIS, technology and weapons, ;
analysis, strategy and futures;
the Covid-19 pandemic;
energy and environment.
However, in a complex world, categories are merely a convenient way to present information, when facts and events interact across boundaries.
The information collected (crowdsourced) does not mean endorsement.
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 7 December 2022, China’s president Xi Jinping received a royal welcome at his arrival in Saudi Arabia for a three days state visit. State visits between China and Saudi Arabia heads of state have taken place since 2016.
Furthermore, during this state visit, President Xi was the first Chinese head of state to attend a Gulf Cooperation Council summit. That session, taking place in Riyad, included very high levels representatives from the whole Middle East-North Africa region (“President Xi Jinping attends first China-GCC summit and delivers keynote speech”, Ministry of Foreign Affairs of the People’s Republic of China, 2022-12-10).
Nowadays, China is the main importer of the Saudi oil production. China buys almost 18% of it. Yet, if energy was a major feature of this visit, artificial intelligence (AI) issues were also a central topic of the visit.
Chinese military drones and surveillance technologies’ sales were also part of the signing spree, which is said to reach around 30 billion dollars in value. For example, Huawei, the Chinese AI giant, signed a memorandum of understanding for the development of installations in several Saudi cities (“Xi visit: Saudi Arabia inks deal with Huawei, despite US fears”, Asian Financial, 9 December 2022).
In other words, this state visit was literally a formalization of the convergence of the Chinese Belt & Road Initiative (BRI) and of the Saudi AI development. This convergence has profound geopolitical consequences. Those are especially important in terms of the reinforcement of Chinese influence in an area that had been so far largely oriented towards the U.S. and of the related transformation of the Gulf states.
Those AI negotiations become de facto a policy when the Saudi minister for information and communication technology and the Chinese minister of industry and information technology signed a common strategic partnership plan (Rawan Radwan, ibid).
It is in this context that Huawei, the AI giant, signed a memorandum of understanding. The latter is about the development of facilities in Saudi cities and of cloud computing. This comes after Huawei built 5G infrastructures in several Persian Gulf countries (Aziz El Yaacoubi and Edouardo Baptista, “Saudi Arabia signs Huawei deal, deepening China ties on Xi’s visit”, Reuters, December 8, 2022).
This dynamic imbues the development of the mega project Neom: the integration of four new cities into a smart urban complex.
Located on the Red Sea, close both to Jordan and Egypt, Neom is going to be a giant laboratory for the diversification of the Saudi economy through innovation. It will notably explore adaptation paths to the raging effects of climate change through the use of AI (“Saudi Arabia ‘not building The Line” but AI is, says NEOM executive”, Arabian Business, November 30, 2022).
In other words, the integration of AI aims at turning Saudi Arabia into a 21st century great power. The Kingdom uses its oil rent to transform from an energy giant into a major digital power.
In this context, the Chinese experience of investing massively to become the world leader in the AI field in 2030 will certainly be a strategic asset for the Saudi party. The same is true of the Chinese experience in installing networks of AI “city brains” (Jean-Michel Valantin, “The Chinese Artificial Intelligence Revolution”, The Red Team Analysis Society, November 13, 2017).
The BRI and the Arab states
As it happens, those numerous Chinese-Saudi cooperations in AI appear as a new dimension of the convergence between the Saudi Arabia 2030 grand strategy and the Chinese Belt & Road Initiative (BRI) (Jean-Michel Valantin, “Saudi Arabia and the Chinese Belt&Road : The Great Convergence”, The Red Team Analysis Society, March 11, 2019).
The BRI, deployed since 2013, is a strategy aimed at ensuring for China the constant flows of energy resources, commodities and products. Those flows are necessary to the current industrial and capitalist development of the 1,4 billion strong “Middle Kingdom”. (Jean-Michel Valantin, “China and the New Silk Road – From oil wells to the moon … and beyond”, The Red Team Analysis Society, July 6 2015). Since then, it has attracted the interest and commitment of numerous Asian, African, Middle-Eastern European and South -American countries.
This is why we qualify some spaces as being “useful” to the deployment of the BRI. And each “useful space” is related, and “useful”, to other “useful spaces”.
From Saudi Arabia to China, and Back
Hence, the Persian Gulf and its states are fundamental “useful spaces” for China. As a result, Saudi Arabia is de facto of great interest for the BRI: Saudi Arabia, the other Gulf states and Arab states become a useful space. Indeed, the BRI increases the Saudi capabilities to respond to the Chinese energy needs.
Coupling China, the Gulf and the Mediterranean world
One must add that the geography of Saudi Arabia furthers the opening of the maritime BRI to the Red Sea, thanks to the Saudi ports, such as Yanbu and Jeddah.
In other words, the BRI improves the access of the Chinese civil fleet to the Red Sea. As a consequence, the Chinese convoys can access the Suez Canal and thus the Mediterranean Sea. Thus, coupling the BRI and Saudi Arabia further open the markets of the Middle East, North Africa and Southern Europe to China.
From Huawei, with Love
In this context, the Saudi- Huawei deal is of particular interest, because of the company’s expertise in “intelligentizing” pipelines.
Furthermore, Huawei is already active in Saudi Arabia. The company has a contract with the Saudi Railways. It is also building a huge battery energy storage on the Red Sea. The project, based in Neom, complements the installation of a mammoth 400 MW solar plant (Dale Aruf, “China’s tech outreach in the Middle East and North Africa”, The Diplomat, November 17, 2022).
This deployment supports the extension of the Chinese influence in and through the Saudi Kingdom. This whole dynamic is self-reinforcing despite the strong reluctance of the United States to accept this geopolitical convergence.
From U.S. influence to Saudi-China influence
Indeed, the energy and AI Saudi Arabia-China great convergence is a major strategic shift that weakens the U.S. influence both in the Middle-East and in Asia.
As it happens, the digital Silk Road has multiple incarnations, especially through the extension of fibre optic cables networks (Jonathan E. Hillman, ibid).
The most important of these cables is the Pakistan & East Africa cable connecting Europe (PEACE). It connects China to Pakistan then to Djibouti and Egypt, then to Europe. At the same time, Huawei is developing technology centres in eight MENA countries, including Tunisia, Turkey and Egypt. Nine other cables connect MENA countries with China. Meanwhile, Chinese companies multiply high-tech deals with Israeli firms (Dale Aruf, ibid).
The same is true with Beidou, the Chinese global positioning system that competes with the American GPS. Since 2017, China has launched the China-Arab states Beidou Cooperation Forum. Saudi Arabia, Oman, Algeria, Lebanon, Morocco now deploy Beidou (Dale Aruf, ibid).
Undermining U.S. influence
So, from a geopolitical point of view, the Arab choice of Chinese technology is deeply meaningful. Indeed, those countries adopt those Chinese technologies, while the United States ban Huawei, ZTE and other Chinese telecommunication companies from their territory (Diane Bartz, Alexandra Alper, “U.S bans Huawei, ZTE equipment sales, citing national security risks”, Reuters, December 1, 2022).
Meanwhile, the U.S. political and trade authorities ban any export of U.S. advanced technology, including microchips for AI.
However, the Arab states multiply giant deals with those very same Chinese companies that the U.S consider as a potential danger (Rishi Iyengar, “Biden short circuits China”, Foreign Policy, 28 October 2022).
Those Arab strategic choices are also supported by the fact that China does not condition its economic cooperation on political and moral obligations. So, the cooperation between the Middle Kingdom and the Arab states is very fluid (Loretta Napoleoni,Maonomics, Why Chinese communists make better capitalists than we do ?, Seven Stories Press, 2011).
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, Saudi Arabia, the Gulf states and other Arab 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). By doing so, the convergence of the development strategies of China and of the Arab states undermines the U.S. influence in the MENA region.
So, while defeats and dramatic blunders in Iraq, Libya, Syria, Afghanistan weaken the U.S. influence and power, the Arab states acquire new tools of economic development from China.
In this regard, we have to remember that the whole Persian Gulf region is under the direct U.S. military influence. This influence is exercised through the fifth fleet, the land and air forces and a network of bases. All those forces are under the direct authority of the U.S. Central Command.
How can individuals and small business leaders protect themselves against the crises and upheavals that seem to be imposed on them? Can they take advantage of tools that are generally reserved for state actors, especially security forces, and sometimes for large companies? Can such a tool, early warning, be useful for individuals and small business leaders, and how? How can early warning be made available to everyone?
How can we reduce the plight that so many people face due to the ever-increasing prices of energy and electricity, for example in Europe? How can we mitigate the negative effects resulting from other problems and challenges, such as climate change, war, water and resource scarcity, etc.?
The answer to these key questions lies in the use not only of early warning but also of actionable early warning. We explain first what is actionable warning.
We then turn to a core component of the early warning process, action. With the example of the energy insecurity and more particularly the rise in electricity prices, we explain that actionable early warning must not only look outwards to the world but also inwards to response capabilities. We stress that empowerment of individuals and small business leaders is a key component of a successful actionable early warning process applicable to all. We compare two cases to be able to draw actionable lessons: the broken bakers versus the successful wool manufacturer.
In a concluding third part we outline a roadmap for a realistic and practical use of actionable early warning for individuals and small businesses and stress the importance to embed it at local level.
What is actionable early warning?
Early warning, what is it for?
Early warning, or better strategic foresight and warning, is the art and science to avoid surprise, notably unpleasant ones. It is defined as:
“An organised and systematic process (including analysis, intelligence) that aims to reduce the uncertainty inherent in the future” (Fingar, 2009). “Its purpose is to enable decision-makers to take their decisions early enough to ensure that these decisions are implemented in the best possible way.” (Davis, Grabo, Knight)
Early warning, who is it for?
Most of the time, when we design an early warning system, or make early warning analysis, we do so for state agencies and other international bodies, for governments and officials, or for relatively large companies.
Yet, every human being, every organisation must face the uncertainty inherent in the future, and take decisions to govern its own life and activity, so as to live as best as possible and ultimately to survive.
Thus, if current practice and methodology has been developed and refined for state actors, most often in military affairs and international security, actually, everyone could and should use early warning.
Indeed, often without knowing it we, as individuals, already use early warning systems of a sort. When we consider weather forecast to choose our clothes, or activities, we use early warning. When we look at traffic situation and forecast, similarly, we use early warning.
Hence early warning is for everyone, even though it is knowingly used, most of the time, only by specific actors. Yet, it is also different according to who is using the warning. Why is that so and in which way?
The promise of actionable early warning
It is clear from the definition above that early warning must be practical or rather actionable.
In other words, it must lead to the possibility for actions. When one receives a warning, then one must be able to act to prevent or mitigate the negative impact of the object of the warning or, on the contrary to build upon the positive consequences.
For example, if someone gets a warning about heavy rain during the afternoon then s/he may decide to take an umbrella if s/he has to get out, or postpone getting out if possible. If a state counter-terrorist apparatus receives a warning about a terrorist attack, then it will deploy its counter-terrorist strategy from carrying out a counter-terrorist operation to implementing measures to protect citizens. Now, if a warning about a terrorist attack reaches an individual, for example through the alarm system of a state, then the individual will solely follow the instruction of the state, possibly staying at home, being extremely careful when traveling, paying attention to abandoned objects etc. It will not, however, be able – nor allowed – to carry out most of the counter-terrorism answers endeavoured by a state.
What these short examples highlight is that the types of answers resulting from a warning change according to the type of person or actor receiving the warning. Hence a warning must also consider the range of responses available. As a result the process of early warning, if it wants to be actionable, must take into account the capabilities and possibilities of answers and actions.
The responsibility to warn
The responsibility for warning, and thus for setting up and carrying out the process of early warning, and which process, also varies according to actors and to their normative duties within their polity. As a result, if early warning is fundamentally for everyone, the issues to which one pays attention in terms of warning vary. These issues depend upon the social contract that exists between political authorities and those they rule, as well as upon the capacity of the said political authorities to ensure the security of their citizens according to the social contract.
Now, in an ideal legitimate and efficient polity, political authorities will be responsible for protecting the ruled from foreign enemies, for ensuring civil peace and order at home, as well as for the conditions for material security, including customary security(1). In this ideal case, political authorities are indeed those who are responsible for warning on the issues that constitute their fundamental mission, i.e. the various aspects of security.
However, for many reasons, which are beyond the scope of this article, we live in polities that are far from being ideal. In that case, those who are ruled may also have to start enlarging the domain to which they must apply their own typical early warning. They need to also look at security, from geopolitics to resources scarcity through climate change. When survival is at stake, it is even more important to be able to make this kind of transition – from waiting for political authorities to carry out all actionable early warning to also doing it oneself – as quickly as possible.
In such cases, how can individuals and managers of small companies carry out actionable early warning notably on conventional and unconventional security?
The key is action
The two indispensable faces of actionable early warning
Considering the role and promise of actionable early warning, if we think about the actions that need to be taken in regard to possible future events, then this means that actionable early warning must have two components: one that is looking outward to the world for those coming events and one that is looking inward at one’s capacity for action.
Looking outward to the world and reality
The first component of an actionable early warning process is probably the most obvious and best known. It implies to look at the outside world and to make judgements regarding the future as resulting from future dynamics of world events. This is true whatever the issue of concern.
For example, if we consider the war in Ukraine and the responses to it decided by the U.S., the European Union and its members states, one such still generic warning could have been at the end of February 2022:
“Considering the attempt to transition to renewable resources, the rising effects of climate change, the international need for energy, the tense international context and the war in Ukraine and responses to it, it is almost certain that the prices of energy in general and electricity in particular will skyrocket notably in energy-poor Europe within the next twelve months and that the very high prices will lastfor at least the autumn and winter months 2022-2023, and possibly longer“.
For a proper actionable warning, this still general statement would then need to be refined. It would need to give, notably, an idea of the rise of energy and electricity prices that could be expected, a more precise onset for and then duration of the increase in energy prices, according to various variables and thus scenarios.
These warnings were done in more or less specific and thus useful ways. Indeed to be truly useful, thus actionable, early warning also has to account for a second component, the range of possible actions.
Looking inward, at the range of available responses
Let us imagine that the person receiving a warning similar to the one presented above is an individual or the owner or manager of a very small company such as a bakery or a 10-employees company in any field, or, a craftsman. When these people read about the warning, they may either consider it or refuse it. We shall not look at this second case, as we already explored various possible instances leading to the failure to consider warnings.
Let us, thus, imagine these people decide to consider the warning. The warning can truly become actionable only if those who pay heed to it can envision responses and then carry them out.
If, for example, they only think about a diplomatic solution to a crisis, then the possible response appears as being so far away from what they can actually do, that the warning will be completely useless.
Thus, we need to have a relation between the warning and the responses available. Hence, we need to have decision-makers, here individuals and small business leaders, who not only receive the warnings and pay heed to them, but are also aware of a range of possible responses they can imagine and implement.
Empowering individuals and business leaders
The power of individuals
If you are an individual, your capacity to act, actually your power, is very small compared to a state. Yet, it is not inexistant.
At first glance, in the case of the example we use for this article, it seems that an individual does not have much power to make the war in Ukraine stop, nor to influence any government or supra-national body so that they change their policies and actions. The context appears as quite set and very extraneous. Thus, it seems that, as an individual, you need to take as a fated constraint this very rise of energy and electricity prices that is coming, then, writing in January 2023, that is upon us and is very likely to last, despite possibly temporary decrease (such as the one that started at the end of December 2022).
This means that, apparently, the only actions available to you are to do your best to reduce your energy bills in general, and more particularly your electricity bills. Furthermore, in some countries and geographical areas, you may need to get ready to face shortages.
According to how close your polity is from an ideal polity, you will also tend to expect your political authorities to act in such a way that you are protected from the rise. Yet, the very fact that you need to face such energy prices increase in itself, questions the ideal quality of the system within which you live.
Actually, your power is more complex and stronger than what you think. The power of an individual, most of the time, depends upon its revenues, its material assets, its status, its support social network, as well as on its knowledge, acumen, imagination, strength and faith, which can be seen as immaterial assets. These various elements are often linked, but not always, and not always in an ideal and logical way.
It is thus all these dimensions of its power that an individual can use and combine to answer a threat or, more broadly, future uncertainties.
Meanwhile, the goal that must be achieved through the responses to avoid the threat – initially the surprise – is also more complex than just reduce energy consumption and thus energy bills in general. And in considering complexity may reside the solutions. What an individual needs to do is to reduce the cost of its energy mix, directly and indirectly, through developing a related range of action on the short, medium and long term.
Because now we also have a better perception of the available power of an individual, we can add that the reduction of the cost of the energy mix must be accomplished through actions taken across the various elements of the available individual’s power on different time horizons.
This may mean, for example, moving home and region, taking advantage of home-working and negotiating to see your employer paying for your energy bill. This may also mean joining consumers associations, lobbies, communities of interest and political organisations, taking on new roles within your community, etc. For instance, looking at ways to produce energy through joining collective networks and communities acting in this direction may also become an interesting way forward to handle energy insecurity. We can think to the production of biogaz by collectivities, which could also consider involving individuals as producers (GRDF, “Du gaz vert produit directement par les habitants de Lamotte-Beuvron“, 22 February 2022). Overcoming energy insecurity will imply mixing various solutions according to your power.
In any case, this implies that you must first be aware of whatever power you have, while understanding better the threat(s) and objectives. Power comes first because without awareness of what you can do, then no answer can be imagined and no solution can appear.
The power of small companies and their leaders
If you are a small business leader, the picture is quite similar, but you have more power than an individual.
You have a larger network of relations constituted by your employees if any, your customers and suppliers, the various people with whom you interact at the local political level and within the administration, to which can be added various key social networks such as, for example, chambers of commerce, trade and industry, i.e. the leaders of other small companies similar to yours.
However, because you are a professional, you may also have to face a larger and wider impact of the energy and electricity price’s rise. At worst, this impact may mean getting out of business rapidly, which then, in turn, will translate into impacts at individual level.
As in the case of an individual, you need first to be aware of your power and thus capability and range of answers to be able to imagine and implement responses. Without this empowerment, warnings will be of no use to you as they cannot be translated into action.
Let us now turn to two different cases to draw lessons for an actionable early warning.
Two cases: the broken bakers and the thriving textile manufacturer
The two cases we examine below exemplify two ways to face the new energy insecurity for industries using energy rather intensively.
Unfortunately, energy being at the core of our model of development, indeed being indispensable for any evolution and for survival, most human activities are energy intensive in one way or another, directly or indirectly (Thomas Homer Dixon, The Upside of Down: Catastrophe, Creativity, and the Renewal of Civilization, Random House Canada, 2006).
Our two cases will first show that a catastrophic situation and possibly ending is not a fatality. Meanwhile by contrasting two ways to face the new energy insecurity, they will help us finding out what must be done in terms of response and thus actionable early warning.
The Broken Bakers
Over the Summer 22, across Europe, multiple cases of bakers going bankrupt because of their soaring energy bills emerged.
Each time the story is the same. Bakeries have a very high energy consumption for cooking and refrigeration. In 2022, they saw energy bills skyrocket, being multiplied up to 10 or 12 times compared with 2021.
In the example given below of a French baker, assuming the electricity consumption remained the same for October 22 and December 22, the price of electricity, excl. taxes, rose from 0,112€ per kWh (837,35/ 7456) on 24 October to 1,372 € per kWh (10735,48/ 7456) on 24 December 2022 (CNews, 2 January 2023).
Meanwhile, bakers must also face the rising cost of the ingredients they use.
Meanwhile, they cannot increase the prices of bread proportionally. Indeed individuals and families purchasing bread and related products also have to face inflation and increase in energy prices. Thus, they would not buy bread at a high price, for example 3 euros a baguette in France (video below, InfoFrance2, “Un boulanger de l’Oise ne peut plus payer ses factures”, 3 January 23) or 5 euros for a normal loaf of bread in The Netherlands (Reuters, “Bread sales can’t cover energy bill at family-run Dutch bakery”, ibid). Bread would become a luxury product and the lowering of the quantity sold would offset the rise in price.
As a result, bakers tried various strategies to mitigate the rise of energy prices, from renegotiating individually their contracts with energy providers to protests and actions through media interviews to obtain help from governments.
How each industry and each company will be able to handle this substantial rise will depend on their energy mix, the share of energy in their production cost, their size, their treasury, other mitigating governmental measures, etc.
Furthermore, this string of events takes place within the framework of the ideology of infinite growth – initially a financial and speculative approach, pervasive within a large part of the Western world. According to this ideology, one must not only make a profit sufficient to see the owner of a company live comfortably of its craft and work, and thus have a sustainable activity, but one must also increase these profits permanently and then make sure there is a lasting growth of the growth of profits. Hence, ideologically, companies such as small bakers who would need to adapt to “only” having a sustainable activity may balk and perceive themselves as being in worst conditions than they really are. They may also face problems with other actors as their activity does not follow the normative ideology of infinite growth.
As a result, domestically, companies are likely to try passing on the largest possible part of the energy and resources price rise on to the buyer, which, at the end, will be the final consumer, i.e. individuals. At country level, we thus find ourselves faced with the spiral of inflation added to an ever rising national debt – to pay for the price of the MWh offered by governments.
Internationally, those small companies that export will also attempt to pass their costs onto their buyers, but there, they will most probably lose markets, as other countries, notably in Asia, but also the U.S., did not have to face the same costs. And if they do not pass on the costs, then they will have less means to invest and thus become also less competitive (if no other measures are taken). Hence at country level, exports will diminish. Thus, the trade balance will also diminish. All together will lead to shrinking current accounts, thus, ultimately to a dwindling income for each country and possibly to involution.
Find out more on consequences at national level in our strategic foresight experiment about the future of the modern state: The Chronicles of Everstate.
The fear of electricity shortage in France in 2022-2023, added to winter times, first boosted the company’s sales and thus its production, by 30% to 40% (BFM TV special crise énergétique, Ibid.). This led the enterprise to hire a further 30 employees, i.e. seasonally a 66% increase of its workforce (Ibid.).
In times of energy insecurity, such an evolution could have had a catastrophic impact on the treasury and finance of the company.
However, the founder of the company truly believes in sustainable economy and has really put respect for the environment at the heart of the enterprise’s philosophy since the creation of the business in 1983 (Missègle, engagements). Hence, since 2007, she has invested in solar energy aiming at environmental friendly energetic independence (Ibid.).
In 2021, the company deployed its new 100kWp rooftop solar power plant deployed with a further 53kWc extension planned (Sirea Group press release, 5 October 2021). Hence with its 1000 square meters photovoltaic panel park, the company aims to reach 70% auto-sufficiency for its production and to sell electricity to the national grid during the week-ends (La Dépèche, “Castres. Missègle…) . Meanwhile, its buildings are not only environmental friendly but also designed to allow for a truly convivial space to live and work (Ibid.).
We are far from the green-washing so cynically spreading in the business world.
Hence, the new energy insecurity is very likely not to hit Missègle negatively (as long as its solar power plant resists extreme weather events for example). The increase in turnover will most probably not only offset any rise in the cost of electricity – for the part it does not produce – but also allow it to further develop and thrive.
Meanwhile, for the country, companies such as Missègle do not weight on the real national wealth – which includes the nation’s natural endowment. Furthermore, through taxes, employment, electricity production and constructive involvement in the local social fabric, such businesses contribute to increase national wealth.
Lessons from the two cases
Which lessons can we learn from our two cases?
On the one hand we have companies that did not use foresight. They obviously did not either use any actionable early warning. Early warning should have, at worst, been received and considered by these companies’s decision-makers in March 2022, or, better, in November/December 2021.
Instead those business leaders waited for the crisis to hit and then started acting rather classically, struggling to force their political authorities to help them in facing the consequences of governance decisions. This is indeed, as we saw, a proper reaction in an ideal polity. Yet, the very decisions the multiple European political authorities took regarding notably the war in Ukraine, obviously without planning ahead for the multiple consequences their own citizens would have to suffer, highlights the fact that we are not in an ideal polity. Hence, businesses and individuals must take this fact into account if they want to minimise the negative impact of governance decisions on their lives and survival.
These business leaders were not empowered, and, as a result, could only consider classical means of actions of the type adequate for an ideal polity.
If a majority of individuals and businesses behave as in our first case, the collective results at country level may be dire, leading straight, as warned by the Medef, to European deindustrialization and, as seen, to involution. Note that in terms of world order, the U.S. might thus find itself with greatly weakened allies, which may have as consequence to favour the strengthening of the very order America wants to subjugate (see Helene Lavoix, “The American National Interest“, The Red Team Analysis Society, 22 June 2022).
In turn, the prospects for bakers, small and large companies, and individuals located in those countries hit by energy insecurity, such as European ones, become more somber with time. Indeed, our fate also depends upon the relative power of our country in the international order. A vicious cycle could becoming entrenched.
It thus fully included strategic foresight – consciously or not, formally or not – on a major issue in its management. Through its strategy to reach energetic independence, it showed an awareness that we do not live in an ideal-type world. It courageously took responsibility for its destiny, increasing its self-reliance regarding worldwide political authorities that are obviously unable to handle efficiently the climate and environmental crisis (Ibid.). It felt sufficiently empowered to act. Furthermore, it did so in a constructive and positive way, embedding itself within the fabric of society at local and national (through the electricity grid as well as through taxes) level.
Once the energy and electricity prices’ crisis hit, this company – and others similar – can take advantage of the new conditions, using – even unknowingly – actionable early warning to adapt, so as to produce and sell more. Meanwhile, it also have the means to further adapt its energy mix to offset adverse impacts of the energy crisis and, on the contrary, to transform them in opportunities.
From outside, in the second case, we do not know how formal, conscious or unconscious was the use of actionable strategic foresight and early warning. Methodology of strategic foresight and warning may very well never have been implemented, and intuition and conviction may have presided to successful management. And this is where one of the strengths of actionable strategic foresight and early warning lies: it gives us the possibility to systematically benefit from what, without actionable early warning, can only haphazardly be achieved through intuition. It helps us supplementing, checking and enhancing natural intuition and acumen.
In the first case, most companies and individuals have very few means of action, and thus little power. Furthermore they limit their power by not using tools such as actionable foresight and early warning and through the use of an inadequate frame of reference (thinking they are in an ideal polity).
In the second case, actionable foresight and then early warning are made possible because means of action are available. Those were created well before the crisis by a proper anticipation, daring to look at reality and not marred in utopian rosy wishful thinking. The whole endeavour was also grounded in strong beliefs, coherent with the company’s foresight, and related commitment. We thus see a virtuous cycle being set up between anticipation and action, a model upon which we can construct a similar virtuous cycle with organised actionable strategic foresight and early warning and actions.
The power available to companies and individuals that would belong to the second type of actors is far greater than what is available to the first type of actors. And this power will grow both in absolute and relative terms, as successfully anticipating actors can better withstand threats and disasters and sometimes turn them into opportunities.
Road map for a realistic use of actionable early warning for individuals and small companies
As seen above, actionable early warning for individuals and small companies will critically need to look both outwards to the real world, for issues related to security, including geopolitics, and inwards to the response capabilities of each.
The warnings delivered will absolutely need to consider the answers available to be truly actionable.
Empowerment will also need to be a key aspect of the early warning process. It can be achieved through, for example, the identification of new possibilities of responses, as well as through re-embedding people within their community, which in turn strengthens the social fabric.
Obviously, in many if not most cases, individuals and small businesses may not be able to afford the cost of an expert in strategic warning specialised in conventional and unconventional security (as average around 1500 € to 2000 € a day excl. taxes and travel expenses, varying widely according to length of mission, to experts and their experience and education level, to the companies providing the consulting… and to available budgets).
However, mutualised solutions at local level of governance and through chambers of commerce and industries and networks of peers can be designed that could allow all to benefit from actionable strategic foresight and early warning. Furthermore, empowerment should also result from collective thinking and then, possibly, action. Embedding the actionable strategic foresight and early warning process at the local level, involving local actors from inhabitants and businesses to those responsible for local governance should also, in itself be beneficial as it will strengthen the social fabric and thus make communities stronger and more resilient.
It will be useful and practical to start first with a specific issue of concern that matters to stakeholders. Then, once first concrete results start being achieved, the process can be broaden to other issues relevant to the community of interest.
The foresight and early warning process will need to start as early as possible, to make sure to avoid surprises. Even if crisis has already struck, it is still beneficial, and even necessary, to carry out early warning. Indeed, this is the only way to make sure current decisions are correct and that further unpleasant surprises will be avoided. In general, the sooner the early warning process starts, the better: the more actions are available, and finally the less power must be spent. Nonetheless, can it be too late sometimes for actionable early warning? Yes, and this is one more reason to start as soon as possible.
Through the use of actionable foresight and early warning adapted to the reality of actors, then a virtuous cycle can be triggered. That cycle will not only be protective but also strengthening, while ripple effects will also benefit the whole polity.
(1) For this last point: “The third obligation of the ruler is to behave in such a way as to contribute to the material security… of the subjects. … security against supernatural, natural and human threats to the food supply and other material supports of customary daily life.” Barrington Moore, Injustice: Social bases of Obedience and Revolt, (London: Macmillan, 1978: 21-22); for more on the theme of the ruler, its obligations, the social contract etc. see also and notably, Max Weber, Le savant et le politique, (Paris : 10/18, 1963) originally «Wissenschaft als Beruf » & « Politik als Beruf » 1919; John S. Migdal, Strong societies and weak states : state-society relations and state capabilities in the Third World (Princeton: Princeton University Press, 1988); John Nettl, “The state as a conceptual variable,” World Politics, vol. XX, N° 4, July 1968, pp. 559-592; Thomas Ertman, Birth of the Leviathan: Building States and Regimes in Medieval and Early Modern Europe. Cambridge, UK ; New York: Cambridge University Press, 1997; Helene Lavoix,“Identifier L’État Fragile Avant L’Heure: Le Rôle Des Indicateurs De Prévision“, Edited volume, Etats et Sociétés fragiles (Agence Française de Développement and French Ministère des Affaires Etrangères) – January 2007.
(2)We have no affiliation nor link of any kind with any of the companies mentioned in this article. Businesses and companies are only referred to for the sake of examples.
We designed the introductory programme. Then, in Tunis, we trained over two days the General Directors of various Ministries and Agencies of the Tunisian Government of the current promotion of the Institute of Administrative Leadership of the ENA.
The trainees created through their focused attention, interest, commitment and enthusiasm, including for the practical exercise, a fantastic training experience.
Hopefully, this first cooperation will be followed by many others and will contribute to spread the practice and use of actionable early warning and strategic foresight within the Tunisian government and beyond.