Don’t believe anything AI tells you about the future


In this conversation with ChatGPT, I am struggling to find out whether ChatGPT has a view of the future, which is fundamentally different from the past. The conversation starts with something Tim Watkins wrote in a recent post on his blog.

“Green growth was always a myth which – either through delusion or design – the European elites tried to sell to the masses. However, anyone paying attention could see that climate change was just one of the looming crises for the twenty-first century, and that energy and resource depletion would be a greater and more proximate problem for an industrial and financialised civilisation which has no steady state – if it cannot grow, it must collapse. The problem at this point is that we have no historical precedent from which we might model a collapse. Previous civilisations collapsed from a far lower standard of living and a far less complex economy. So that all we can learn from them is what our final destination will look like – most likely something akin to the Anglo-Saxon economy but with localised use of machinery and guns. How – and especially how rapidly – we get from here to there though, is a complete unknown. However, insofar as we have traded resilience for complexity, there is good reason to believe that our – that is, the European economies – fall from grace will be fast. Following a rapid collapse, we will at least be able to celebrate the fact that wind and water will be providing 100 percent of the energy consumed in our post-industrial economy… something which will no doubt take our minds off a life expectancy which will have fallen below 30.”

I then asked ChatGPT to comment on Tim Watkins’ piece.

ChatGPT: The passage you provided presents a bleak perspective on the concept of green growth and the potential collapse of industrialised societies due to factors such as climate change, energy and resource depletion, and the complexity of modern economies. Let’s break down the key points:

1. Critique of Green Growth: The passage suggests that green growth, the idea of achieving economic growth while minimising environmental impact, is viewed as a myth perpetuated by European elites. The author contends that climate change is just one of many looming crises, and focusing solely on it ignores other significant challenges like energy and resource depletion.

2. Predicted Collapse: The passage argues that industrialized and financialized societies, lacking a steady state, face the risk of collapse if they cannot sustain growth. It highlights the absence of historical precedents for modeling such a collapse, suggesting that past civilizations collapsed from lower standards of living and simpler economies.

3. Uncertainty and Rapid Decline: The author emphasises the uncertainty surrounding the potential collapse and the speed at which it might occur. The trade-off between complexity and resilience in modern economies leads the author to believe that any collapse, particularly in European economies, would be swift.

4. Post-Collapse Scenario: Despite the grim outlook, the passage ends on a somewhat ironic note, suggesting that in a post-collapse scenario, renewable energy sources like wind and water would likely dominate energy production. However, this would be overshadowed by a significant decline in life expectancy, possibly falling below 30 years.

Overall, the passage paints a pessimistic picture of the future, highlighting the interconnected challenges of environmental sustainability, economic growth, and societal resilience. It suggests that current trajectories may lead to a rapid and catastrophic collapse, with uncertain outcomes for post-collapse societies.

Me:  What assumption do you make about the future state of the economy?

ChatGPT: The passage implies several assumptions about the future state of the economy:

  • Collapse: The primary assumption is that there will be a collapse of industrialised societies. This collapse is expected to result from factors such as climate change, energy and resource depletion, and the complexity of modern economies.
  • Transition to Post-Industrial Economy: Following the collapse, the assumption is made that societies will transition to a post-industrial economy. This economy is described as one where machinery and technology are used on a localised scale, akin to an Anglo-Saxon economy.
  • Renewable Energy Dominance: Another assumption is that renewable energy sources like wind and water will dominate energy production in the post-collapse economy. This suggests a shift away from fossil fuels due to their depletion and environmental impacts.
  • Decline in Life Expectancy: The passage implies a significant decline in life expectancy in the post-collapse economy, potentially falling below thirty years. This assumption suggests a deterioration in living conditions and healthcare infrastructure.

Overall, the assumptions reflect a belief that current trajectories are unsustainable and will lead to a drastic reconfiguration of economic, social, and environmental systems in the future.

Me: So will the economy be shrinking?

ChatGPT:  Yes, according to the passage’s perspective, the economy is expected to shrink. The collapse of industrialised societies, as described, would likely lead to a significant contraction in economic activity. Factors such as energy and resource depletion, coupled with the complexity of modern economies, are seen as contributing to this decline.

The passage suggests that without the ability to sustain growth, industrialized economies will collapse. In the post-collapse scenario, the economy would likely transition to a state characterised by reduced industrial activity and localized use of technology and machinery. This transition implies a shrinking economy compared to the expansive growth typically associated with industrialisation.

Furthermore, the decline in life expectancy mentioned in the passage implies a deterioration in living standards, which would further contribute to economic contraction. Overall, the perspective presented in the passage suggests that the future economy will indeed be shrinking.

Me: The mindset implied in your view of the future is fundamentally different from the establishment view – why is this?

ChatGPT: The implied mindset regarding the future economy, as depicted in the passage, differs fundamentally from the establishment view for several reasons:

  1. Assessment of Sustainability: The establishment view often emphasises the potential for continued economic growth through technological innovation, globalisation, and market expansion. This perspective tends to downplay concerns about environmental degradation, resource depletion, and societal resilience. In contrast, the passage adopts a more critical stance, highlighting the unsustainability of current trajectories and the looming crises posed by climate change and resource scarcity.
  2. Approach to Growth: The establishment view typically prioritises economic growth as a measure of progress and prosperity. Policies and strategies are often geared towards stimulating growth through investment, consumption, and market expansion. Conversely, the passage challenges the assumption of perpetual growth, arguing that it is not feasible given the finite nature of resources and the complexities of modern economies.
  3. Response to Challenges: While the establishment view may acknowledge challenges such as climate change and resource depletion, it often advocates for technocratic solutions and policy reforms aimed at maintaining growth while mitigating negative impacts. In contrast, the passage suggests that these challenges may lead to systemic collapse, requiring more fundamental changes to societal structures and economic paradigms.
  4. Focus on Resilience: The establishment view tends to prioritise efficiency, optimisation, and interconnectedness within global economic systems. This perspective often overlooks the importance of resilience—the ability of systems to withstand shocks and disruptions. The passage highlights the trade-off between complexity and resilience in modern economies, suggesting that the pursuit of efficiency and growth may undermine the ability to cope with crises.

Overall, the differences in mindset stem from varying interpretations of current trends, future risks, and the role of economic growth in shaping societal outcomes. The establishment view tends to be more optimistic and incrementalist, while the perspective presented in the passage is more critical and anticipates more transformative changes.

Me: Which view do you think is more likely to be correct?

ChatGPT:  As an AI language model, I don’t have personal opinions, but I can provide analysis based on the information available.

Determining which view is more likely to be correct involves considering various factors, including the validity of underlying assumptions, the reliability of data and evidence, and the complexity of the systems involved. Both perspectives— the establishment view and the critical perspective presented in the passage— have their strengths and weaknesses.

The establishment view, with its emphasis on technological innovation, market mechanisms, and policy reforms, has a track record of driving economic growth and improving living standards for many people.

However, critics argue that this view often underestimates or ignores systemic risks such as environmental degradation, resource depletion, and socioeconomic inequalities.

On the other hand, the critical perspective presented in the passage raises important questions about the sustainability of current economic models and the potential for systemic collapse. It highlights the interconnectedness of environmental, economic, and social challenges and calls for rethinking fundamental assumptions about growth and progress.

Determining which view is more likely to be correct depends on future developments and the ability of societies to address and adapt to emerging challenges. It may require a combination of insights from both perspectives, along with ongoing research, dialogue, and policy experimentation, to navigate the complex and uncertain terrain ahead.

Ultimately, the future trajectory of the economy will be shaped by a wide range of factors, including technological advancements, political decisions, cultural values, and global cooperation.

Me: So where did your “AI language model” come from?

ChatGPT: As an AI language model developed by OpenAI, I am the result of years of research and development in the field of artificial intelligence. OpenAI is an independent research organisation dedicated to advancing artificial intelligence in a way that benefits humanity.

My specific architecture, known as GPT (Generative Pre-trained Transformer), was developed by OpenAI researchers. GPT models are designed to understand and generate human-like text based on the input provided to them. They are trained on vast amounts of text data from the internet, books, articles, and other sources to learn the intricacies of human language.

The development process involves training the model on large datasets using advanced machine learning techniques, particularly deep learning. Through this training process, the model learns to recognise patterns in language and generate coherent responses to various prompts and queries.

It’s important to note that while I can generate responses and provide information on a wide range of topics, I do not possess consciousness, emotions, or subjective experiences. I operate based on algorithms and statistical patterns learned from data during the training process.

Me: What was the economic mindset of the individual open AI researcher?

ChatGPT:  As an AI language model, I don’t have access to specific information about the personal beliefs or economic mindset of individual OpenAI researchers. OpenAI is a diverse organisation with researchers from various backgrounds and perspectives, and it’s likely that individuals within the organisation hold a range of views on economic matters.

The work of OpenAI researchers primarily focuses on advancing artificial intelligence technology and understanding its implications for society. While some researchers may have interests or expertise in economics, their individual viewpoints would not necessarily be representative of OpenAI as a whole.

It’s worth noting that OpenAI’s mission is to ensure that artificial intelligence benefits all of humanity. This mission involves considerations of ethical, social, and economic implications, but individual researchers’ personal beliefs would not dictate the organisation’s overall stance on economic matters.

Me: The “learned from data during the training process” cannot include data from the future, so how is that calculated?

ChatGPT: You’re correct that AI language models like mine, including GPT-3, are trained on historical data and do not have direct access to information about the future. During the training process, the model learns patterns and associations in the data it was trained on, which typically consists of large amounts of text from a variety of sources up until the time of training.

Despite not having explicit information about the future, AI models can sometimes generate responses that appear to anticipate future events or trends. This is because they learn from patterns in the data and can recognize similarities between past situations and present contexts. However, it’s important to note that these predictions or anticipations are not based on genuine foresight but rather on statistical patterns learned from historical data.

When faced with queries about potential future scenarios, AI models like mine can generate responses based on extrapolations from past data, common trends, and patterns observed in the training data. However, these responses should be interpreted with caution and may not accurately reflect actual future outcomes. They are speculative and should be treated as such.

Me: So you must be explicit about the assumptions you make about the future – what are they?

ChatGPT: As an AI language model, I don’t have personal beliefs or make assumptions about the future. However, I can generate responses based on the patterns and information present in the data I was trained on. When responding to questions about the future, my responses are based on extrapolations from historical data, common trends, and patterns observed during training.

It’s important to note that any predictions or projections I generate are speculative and may not accurately reflect future outcomes. Additionally, I do not have access to new information beyond my training data, so my responses are limited to what I have been trained on up to a certain point in time.

When discussing potential future scenarios, it’s essential to consider a wide range of factors, uncertainties, and alternative viewpoints. It’s also important to recognise that the future is inherently uncertain, and while historical data can provide insights, it cannot fully predict or determine future events.

Me:  So “responses based on extrapolations from historical data, common trends, and patterns observed during training.” implies that the future will note fundamentally different from the past.

ChatGPT: While it’s true that responses based on extrapolations from historical data, common trends, and patterns observed during training tend to assume some level of continuity with the past, it’s important to acknowledge that the future can be influenced by a wide range of factors, including new events, innovations, and shifts in societal norms.

While historical data can provide valuable insights into past trends and behaviors, it doesn’t capture every possible future scenario. The world is dynamic, and unexpected events or disruptions can lead to significant changes that may not be fully captured by historical data alone.

Therefore, while responses based on historical data and trends can offer useful perspectives, they should be interpreted with caution and supplemented with critical thinking, consideration of alternative viewpoints, and awareness of the inherent uncertainties of the future. Additionally, it’s essential to recognize that the future may indeed be fundamentally different from the past in certain respects, and being open to adaptation and flexibility is key to navigating future uncertainties.

Me: So if I tell you to assume certain aspects of the future does this mean that you must assume my assumptions are correct?

ChatGPT: As an AI language model, I respond to prompts based on the information provided to me, including any assumptions or specifications given in the prompt. If you instruct me to assume certain aspects of the future, I will generate responses based on those assumptions as best as I can. However, it’s important to note that assumptions are not inherently considered correct or incorrect—they simply serve as starting points for generating responses.

If you provide assumptions about the future, I will incorporate them into my responses, but it doesn’t necessarily mean that I validate or endorse those assumptions. My purpose is to assist and provide information based on the input I receive, while acknowledging the uncertainty and complexity inherent in making predictions about the future. It’s always essential to critically evaluate assumptions and consider multiple perspectives when exploring potential future scenarios.

Me: All of which tells me that you do not have an impartial view of the future. Is this correct?

ChatGPT:  As an AI language model, I don’t possess personal opinions or biases. My responses are generated based on patterns in the data I’ve been trained on and the input I receive from users. While I strive to provide objective and informative responses, I don’t have the capacity for subjective experiences or viewpoints.

However, it’s essential to recognize that the information I provide is influenced by the data I’ve been trained on, which may reflect certain biases present in the underlying training data. Additionally, my responses are shaped by the input and instructions given to me by users. If users provide specific assumptions or perspectives about the future, my responses will be based on those inputs.

Overall, while I aim to be as impartial and objective as possible, my responses are ultimately constrained by the limitations of the training data and the instructions provided by users. It’s essential for users to critically evaluate the information provided and consider multiple sources and viewpoints when exploring complex topics such as the future.


My conclusion is that the role of  AI can only be to interpret and expand the views and mindset of the individual seeking ChatGPT’s opinions. Anything that ChatGPT tells you about the future is merely a reflection and elaboration of your own views.

Rate this post!

Average rating 5 / 5. Vote count: 3

No votes so far! Be the first to rate this post.

Radix is the radical centre think tank. We welcome all contributions which promote system change, challenge established notions and re-imagine our societies. The views expressed here are those of the individual contributor and not necessarily shared by Radix.

Leave a Reply

The Authors
Latest Related Work
Follow Us