Evaluating possible impacts is a key component of strategic foresight, early warning and risk management. It is crucial in strategy and, as a result, for strategic planning.

Go directly to Pithia to explore cascading impacts.


Pithia
Initiation, explorationDefine your concern, scenario and image
Cascading impacts

Calvin
AdvancedIndicators, drivers, factors, variables, causal links, models, and graphs.

Kai
AdvancedScenarios narratives

Regina
ScienceGeopolitics, international relations, political science 
SphinxBiasesChallenge your assumptions and beliefs, devil’s advocate
Tip7 Tips for Effective Communication with Chat AI Assistants

Very often we limit ourselves to thinking about the direct impacts of an action or of an event. Yet, impacts, most of the time, go on. We face cascading effects. For an event, a decision, we thus should consider first the direct impacts, then the second-order impacts (the direct impacts of the direct impacts), then the third-order impacts… until the nth-order impacts.

In terms of strategic foresight and early warning, the capacity to explore these nth order impacts is in-built into the use of a proper model. However this assume that such a model has been developed (see our related training course and how our AI assistant Calvin can help you in this regard), which is not always the case. 

As an introduction to the importance of considering cascading impacts, we created an AI-powered form that allows you to explore some direct, second and third-order effects for an event or decision. 

Pithia assists you in exploring 1st, 2d and 3rd-order impacts

Identify the primary decision or event and its context: the basis for your scenarios

Start by clearly defining the primary decision or event that serves as the basis for your scenarios. You can add context or constraints to obtain something more interesting.

For example, the primary event, decision or objective could be:

An EU’s pro-Taiwan stance within the context of Europe’s need for critical commodities.

or more simply US default on its debt

or Very rapid (less than 6 months) adoption of a generalised use of generative IA across companies, NGOs, governments, administrations and public services in the Western world

Determine the immediate or first-order effects

Use the AI assistant to identify direct and immediate effects of the primary decision or event. These effects should be directly attributable to the chosen objective or event. Find out what some of these effects could be:

Explore second-order effects

Next, consider the ripple effects or consequences that arise as a result of the immediate effects. These are the second-order effects. They may emerge as a response or consequence of the immediate effects.

Among those suggested by the AI, choose the immediate or direct effect you wish to explore, cut and paste it in the field below, amend it as you wish. You can also add a direct effect that was not mentioned by the IA. For example, your input could be:

EU’s pro-Taiwan stance: Improved European access to Taiwanese critical commodities: Taiwan is a key producer of critical commodities such as semiconductors and rare earth elements. The EU’s pro-Taiwan stance will improve access to these commodities, which are essential for European defense capabilities.

US default: Internationally, there would be a shift away from the US Dollar as the world’s reserve currency.

Generative IA adoption: Massive loss of jobs for humans. In general higher paid jobs would be more impacted than lower paid manual jobs notably of a craftsmanship type. The effect could be aggravated by the speedy adoption of AI, which would not give people enough time to adjust to the changes.

Discover third-order effects

Repeat the process by identifying additional effects that stem from the second-order effects. These effects should be logical extensions of the second-order impacts, considering the evolving dynamics and interdependencies between various factors.

Choose the second-order effect you wish to explore, cut and paste it in the field below, amend it as you wish. For example, your input could be:

EU’s pro-Taiwan stance: An increase in competition among other global players who rely on these Taiwanese critical commodities.

U.S. default: Significant diminution of the geopolitical power of the U.S.

Generative IA adoption: The employment situation could further exacerbate the already existing wealth gap between different groups in the society 

Tips: Try! The first 4 queries (across all our AI assistants) are complimentary.

For guests: in a form (Pithia), one click on submit [red button] = 1 query – In a chat (Aria, Calvin, Kai, Regina, Sphinx), 1 question and 1 answer = 2 queries.

For additional use, purchase credits access to our AIs. Existing users should log in to their account.

TipsTraining and examples
We trained and tested the AI many times, notably on three issues. These are used as examples to guide you in the AI form. 

  1. An EU’s pro-Taiwan stance within the context of Europe’s need for critical commodities.
  2. U.S. defaults on its debt.
  3. 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! 

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 increased capabilities and advancements but we are not yet into models with real reasoning capabilities. The future nonetheless may surprise us…

Evaluate the long-term implications

Consider the long-term implications of the scenario by examining how the multiple orders of effects interact and influence each other over time. Assess the potential outcomes and consequences on a broader scale, such as geopolitical realignments, economic shifts, or changes in regional dynamics.

Only you can do that, using all the tools available to us, and notably modeling. Maybe an AI in the future will also be able to do it, one day…

Case study – Cascading impacts for a very rapid adoption of generative AI

Output on cascading effects from Pithia (17 May 2023 – using previous GPT3.5 model)

Comments

speaking, keynote, speaker, conference, Red Team, Red Teaming, quantum, AI, climate change, risk, external risk, strategic foresight, futurism, warning, red team, analysis society, consultant, researcher, expert Input Primary Event:

Very rapid (less than 6 months) adoption of a generalised use of generative AI across companies, NGOs, governments, administrations and public services in the Western world.

Pithia:

The direct and immediate effects of a very rapid adoption of a generalised use of generative AI across companies, NGOs, governments, administrations, and public services in the Western world could include:

Test 1

  1. Massive displacement of jobs: AI could automate many jobs, leading to a significant loss of jobs for humans. The effect could be aggravated by the speedy adoption of AI, which would not give people enough time to adjust to the changes.
  2. 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.
  3. 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.
  4. 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.
  5. 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.
  6. Economic benefits: The use of AI could lead to significant economic benefits, such as increased economic growth and reduced costs. The speedy adoption of AI could accelerate these benefits, leading to faster economic growth and development.

In summary, the very rapid adoption of a generalised use of generative AI across companies, NGOs, governments, administrations, and public services in the Western world could have significant and wide-ranging effects, including the displacement of jobs, increased productivity, privacy concerns, cybersecurity risks, ethical concerns, and economic benefits.

Test 2

The direct and immediate effects of very rapid adoption of a generalised use of generative AI across companies, NGOs, governments, administrations, and public services in the Western world would be significant and far-reaching. Here are some possible effects:

  1. 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.
  2. 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.
  3. 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.
  4. 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.
  5. 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.


speaking, keynote, speaker, conference, Red Team, Red Teaming, quantum, AI, climate change, risk, external risk, strategic foresight, futurism, warning, red team, analysis society, consultant, researcher, expert Input direct effect: Massive loss of jobs for humans in the Western World. In general higher paid jobs would be more impacted than lower paid manual jobs notably of a craftsmanship type. The effect could be aggravated by the speedy adoption of AI, which would not give people enough time to adjust to the changes.

Pithia:

The massive loss of jobs for humans in the Western world due to the adoption of AI could have several significant impacts or consequences. Firstly, it could lead to a sharp rise in unemployment rates, which could result in social unrest, poverty, and inequality. This situation could further exacerbate the already existing wealth gap between different groups in the society.

Secondly, the economic impact could be significant, as the loss of jobs would mean a reduced purchasing power for consumers, leading to a decrease in demand for goods and services. This could result in a slowdown of the economy and reduced economic growth, which may cause ripple effects throughout the whole world.

Thirdly, the loss of jobs could lead to political instability, as people who are unemployed or underemployed may become more susceptible to extremist ideologies and populist movements. The rise in populist movements could cause political polarization and social unrest, leading to a breakdown in social cohesion and stability.

Furthermore, the adoption of AI could also have significant geopolitical implications. Countries that are less developed or have a lower level of technological advancement could be left behind, leading to an increased disparity between developed and developing nations. This could lead to a shift in global power dynamics, as countries with advanced AI capabilities may have a significant advantage over those that do not.

In conclusion, the rapid adoption of AI could have significant consequences for the Western world, including economic, social, and geopolitical impacts. These impacts could cause significant uncertainty and instability, and it is important to carefully consider the potential consequences of AI before implementing it on a large scale.

Here we have truly interesting potential second-order effects, that should definitely be taken into account worldwide by political authorities.

However, as far as our IA is concerned, we observe some difficulties to combine different second-order effects: for example, if in the Western world – those countries that adopt rapidly generative AI – the massive job displacement especially of better paid jobs leads both to unrest and to economic downturn, then will the countries having massively adopted AI still have a geopolitical advantage? Further, is it the very way we conceive the international society and the world order that could change?

Again, we are at too general a level to be able to truly use the results obtained to steer policy, yet, what our AI Pithia highlighted is definitely  worth considering and incorporating in our analyses.


speaking, keynote, speaker, conference, Red Team, Red Teaming, quantum, AI, climate change, risk, external risk, strategic foresight, futurism, warning, red team, analysis society, consultant, researcher, expert Input second-order effect:  The employment situation could further exacerbate the already existing wealth gap between different groups in the society

Pithia:

The rapid adoption of generative AI across different sectors in the Western world could exacerbate the existing wealth gap between different social groups. This could happen as a result of massive loss of jobs, especially among those in higher-paying positions. This situation could be aggravated by the quick adoption of AI, giving people little time to adapt to the changes.

The consequences of this scenario could be far-reaching and complex. It could lead to social unrest and political instability, as people who have lost their jobs struggle to make ends meet. There could also be an increase in poverty and inequality, as well as a decline in the standard of living for many people.

Furthermore, the rapid adoption of AI could have geopolitical implications. Countries that are unable to keep up with the pace of technological change could be left behind, leading to a shift in the balance of power. This could result in increased tensions between nations, as well as a rise in protectionism and nationalism.

In order to address these potential consequences, it is essential for governments, policymakers, and businesses to take a proactive approach to managing the adoption of AI. This includes investing in education and training programs to help people acquire the necessary skills to adapt to the changing job market. It also involves being mindful of the potential social and geopolitical implications of AI, and taking steps to mitigate any negative effects.

Here the AI summarises well the situation, then stops short of truly continuing to look at specific and detailed consequences.

GPT 4 -Turbo (actual model – 16 Feb 2024) could be better at this task, or/and we need to improve how we handle the AI model to get better and more specific answers. Alternatively, LLMs – for now – may just not be able to properly handle such tasks and we would need different types of models.


Published by Dr Helene Lavoix (MSc PhD Lond)

Dr Helene Lavoix, PhD Lond (International Relations), is the President/CEO of The Red Team Analysis Society. She is specialised in strategic foresight and warning for international relations, national and international security issues. Her current focus is on the war in Ukraine, international order and the rise of China, the overstepping of planetary boundaries and international relations, the methodology of SF&W, radicalisation as well as new tech and security.

Leave a comment

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

EN