Monday, January 16, 2023

ChatGTP and the Great Reset

With the World Economic Forum's concentration on Artificial Intelligence (AI) as the solution to everything that ails the world, I took my first steps into the AI world to help me to better understand what the technology is currently capable of doing.  As such, I signed up so that I could access the ChatGPT (Generative Pre-trained Transformer) chatbot which was launched in late November 2022 by OpenAI.


According to OpenAI, ChatGPT is a chatbot model which has the capability of interacting with humans in a conversational way just as we interact with each other.  ChatGPT is not connected to the internet so its responses to queries are internally generated.  


Here's a quote from OpenAI's website about how ChatGPT was created:


"We’ve trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer followup questions, admit its mistakes, challenge incorrect premises, and reject inappropriate requests. ChatGPT is a sibling model to InstructGPT, which is trained to follow an instruction in a prompt and provide a detailed response."


We trained this model using Reinforcement Learning from Human Feedback (RLHF), using the same methods as InstructGPT, but with slight differences in the data collection setup. We trained an initial model using supervised fine-tuning: human AI trainers provided conversations in which they played both sides—the user and an AI assistant. We gave the trainers access to model-written suggestions to help them compose their responses. We mixed this new dialogue dataset with the InstructGPT dataset, which we transformed into a dialogue format.


To create a reward model for reinforcement learning, we needed to collect comparison data, which consisted of two or more model responses ranked by quality. To collect this data, we took conversations that AI trainers had with the chatbot. We randomly selected a model-written message, sampled several alternative completions, and had AI trainers rank them. Using these reward models, we can fine-tune the model using Proximal Policy Optimization. We performed several iterations of this process."


Here is a graphic explaining the steps to training ChatGPT:


With that little bit of background, let's look at a sample interaction with ChatGPT.  As I mentioned at the opening of this posting, the World Economic Forum has a fixation on AI, even creating the Global Future Council on the Future of Artificial Intelligence as shown here:



As an exercise, I asked ChatGPT to create a 500 word essay on the negative aspects of the Great Reset, the WEF's other pet project.  Here's what it wrote over a 15 second-long period of time:


"The Great Reset is a term that has been used to describe a proposed global economic and social overhaul that aims to address the issues and challenges arising from the COVID-19 pandemic. While the goals of the Great Reset are commendable, such as reducing inequality and promoting sustainable development, there are also a number of negative aspects that must be considered.


One of the main concerns with the Great Reset is the potential for it to be used as a cover for authoritarianism and the erosion of democratic institutions. The pandemic has provided an opportunity for governments around the world to exert greater control over their citizens, including by limiting civil liberties and increasing surveillance. In some cases, this has been justified as necessary to address the health crisis, but the fear is that these measures will be extended and institutionalized under the guise of the Great Reset.


Another concern is that the Great Reset may lead to increased inequality, rather than reducing it. The most marginalized members of society are often the ones hit hardest by economic downturns, and the Great Reset may exacerbate this. Those at the top of the economic ladder will likely have the resources to recover and may even benefit from the changes, while those at the bottom will be left behind. Moreover, some argue that the Great Reset is a tool for the elite to solidify their power and control over resources, economy and society.


Furthermore, many argue that the Great Reset is focused on promoting an economic model that is not sustainable in the long term. It heavily relies on the expansion of the green economy and the adoption of technologies such as 5G and Artificial Intelligence, but it doesn’t tackle the root causes of environmental problems, such as overconsumption and overproduction. Instead, it might even speed up resource depletion and waste generation, leading to even more environmental problems.


The Great Reset also raises questions about who will control the economic and technological changes it proposes. The private sector will play a central role in the transition to a sustainable economy, but there is a risk that this will lead to corporate capture of the agenda, which will prioritize profits over social and environmental goals.


Additionally, the Great Reset may lead to the loss of jobs and livelihoods as a result of automation and technological change. The shift to a greener economy and the adoption of new technologies will likely require significant changes in the labor market, with many jobs becoming obsolete and new ones being created. However, not everyone will have the skills or resources to adapt, leading to increased unemployment and poverty.


In conclusion, while the Great Reset has the potential to address some of the major issues facing the world today, it also has the potential to create new ones. It is important that the process of implementing the Great Reset is transparent and inclusive, and that the rights and well-being of all members of society are taken into account. There is a need to address the potential negative consequences and make sure that the benefits of the Great Reset are distributed equitably, avoiding exacerbating existing inequalities and environmental problems. Furthermore, the Great Reset's agenda should be held accountable for its actions, ensuring that it serves society and not special interests."


Remember, ChatGPT does not have access to the internet, all of this content is internally generated from what it has learned from its "human handlers".


It's actually pretty hard to argue with ChatGTP's views on the negative aspects of the Great Reset, many of which parallel the concerns about the plan that have been proposed by the "tinfoil hat wearing conspiracy theory crowd".


In a future posting, we'll look at background on OpenAI and help you better understand the role that this organization is playing in the development of Artificial Intelligence and how its leadership views the future.


  1. This is actually quite scary. Skynet among us! Considering Boston Dynamic's robot dog is quite agile, what kind of robot future awaits us?

  2. ChatGPT, as a powerful language model, showcases the capabilities of AI in understanding and generating human-like text. By utilizing platforms like ChatGPT, we can explore the implications of AI in navigating the challenges and opportunities presented by the Great Reset.

    The concept of the Great Reset, with its focus on reimagining systems and addressing global issues, aligns with the potential of AI to revolutionize industries, foster innovation, and promote sustainable development.

    It's fascinating to witness how "ChatGPT Detector" contributes to this conversation, providing insights and resources to understand and harness the power of AI-generated text. Through this collaboration between humans and AI, we can navigate the complexities of the Great Reset and work towards a better future.

    GPT Detector offers a valuable platform to explore and engage with AI-generated text, enabling us to understand the role of ChatGPT in the context of the Great Reset.

    Let's embrace the potential of AI and the principles of the Great Reset to shape a more inclusive, sustainable, and innovative future.