This is an experiment with ChatGPT Plus which uses GPT-4. In this experiment, I started with a news run, a way of looking at the news in a specific way to identify interesting areas of concern related to the Grey Swan Guild, which is a virtual thing tank. I read an interesting article about the power of prediction by social scientists and it illuminated a few ideas that are related to the way the Guild is set up. So I took a couple of sections of the article and added a prompt connecting the idea to the guild and based on the large language model, it generated a cogent essay. That is correct and clear. All the information in the generation is factual, the connection to the article was part of the prompt. Best of my observation, GPT-4 is an improved editor and writer. In this experiment, there are two edits of the same essay, showing how easy it is to manipulate updates to an idea quickly, as if you are working with a good copyriter and editor. I believe this proves the advance of the model, it’s a more useful tool now. I predict that in the next 3 years, the improvement will be exponential. Better zero shot results, better interactions, better folding in of actual information and tests to make more accessible and enjoyable. And enjoyable writing available at speed, under the control of humans. According to the article I used in the experiment, this prediction is probably better than most social scientists can make. That’s because I use the resources of a collective, and I am a computer scientist by training and practice. Let’s take a look at what the experiment entailed.
Editorial Assistance Available.
Model: GPT-4
Robert Tyrie
Act as an editor and science writer. If you understand say yes
Yes, I understand. As an AI language model, I can assist you in both editing and science writing tasks. Please feel free to provide any content or specific topics you'd like me to help with.
Robert Tyrie
Why do we gather people with different backgrounds and skills to think about the world and how to make it better?
Because we can gather to analyze and make predictions to ease uncertainty and to avoid loss and strife.
We do that with relatively simple repeatable microstructure the generate both introspection and extrospection (other spections too).
The Grey Swan Guild is a kind of Polymathic Collective.
"Despite the causal nature of most theories in the social sciences, and the fields’ emphasis on prediction in controlled settings, social scientists’ forecasts were generally not very good.
In both papers, we found that experts’ predictions were generally no more accurate than those made by samples of the general public. Further, their predictions were often worse than predictions generated by simple statistical models.
Our studies did still give us reasons to be optimistic. First, forecasts were more accurate when teams had specific expertise in the domain they were making predictions in. If someone was an expert in depression, for example, they were better at predicting societal trends in depression.
Second, when teams were made up of scientists from different fields working together, they tended to do better at forecasting. Finally, teams that used simpler models to generate their predictions and made use of past data generally outperformed those that didn’t."
The Conversation
https://theconversation.com/the-limits-of-expert-judgment-lessons-from-social-science-forecasting-during-the-pandemic-201130
Title: The Power of Diverse Perspectives: How Polymathic Collectives Improve Predictions
In a rapidly changing world, the need for accurate predictions to guide decision-making and ensure a better future has never been more vital. Harnessing the collective intelligence of diverse groups with different backgrounds and skill sets can improve our ability to analyze, predict, and navigate through uncertainty.
The Grey Swan Guild, a polymathic collective, embraces this concept by bringing together a variety of perspectives to explore complex challenges. This inclusive approach allows for more comprehensive analysis, generating insights that could otherwise be missed.
Research in the social sciences has shown that experts' predictions are often no better, and sometimes worse, than those made by the general public or simple statistical models. However, there are reasons to remain optimistic about the potential of expert collaboration.
Firstly, predictions tend to be more accurate when individuals possess specific domain expertise. For example, someone with expertise in depression would be better at predicting societal trends related to this condition.
Secondly, interdisciplinary collaboration between experts from various fields has been shown to improve forecasting accuracy. This synergy facilitates a more comprehensive understanding of complex issues and can lead to more reliable predictions.
Lastly, teams that employ simpler models and leverage past data typically outperform those that do not. By focusing on essential factors and grounding predictions in historical trends, these teams can often generate more accurate forecasts.
In conclusion, polymathic collectives such as the Grey Swan Guild demonstrate the value of bringing together diverse perspectives to tackle complex challenges. By fostering collaboration among experts from different domains and emphasizing data-driven, simple models, we can improve the accuracy of predictions and make more informed decisions about our collective future.
Source: The Conversation
[https://theconversation.com/the-limits-of-expert-judgment-lessons-from-social-science-forecasting-during-the-pandemic-201130]
Robert Tyrie
Change depression to computer science and rewrite. Add a continuous concrete metaphor across the essay to explain the power of the guild.
Title: Navigating the Maze of Complexity: How Polymathic Collectives Illuminate the Path to Better Predictions V2
Navigating the intricate maze of today's world requires accurate predictions to make informed decisions and build a better future. Just as a group of diverse individuals can better solve a complex maze by sharing their unique perspectives and knowledge, the collective intelligence of people with different backgrounds and skill sets can improve our ability to analyze, predict, and overcome uncertainty.
The Grey Swan Guild, a polymathic collective, embraces this concept by bringing together a variety of perspectives to explore the labyrinth of challenges we face. This inclusive approach allows for a more comprehensive analysis, shining light on hidden pathways and generating insights that could otherwise remain in the shadows.
Research in the social sciences has shown that experts' predictions are often no better, and sometimes worse, than those made by the general public or simple statistical models. However, there are reasons to remain optimistic about the potential of expert collaboration as a guiding light through the maze.
Firstly, predictions tend to be more accurate when individuals possess specific domain expertise. For example, someone with expertise in computer science would be better at predicting societal trends related to technological advancements and their impacts.
Secondly, interdisciplinary collaboration between experts from various fields has been shown to improve forecasting accuracy. Just as multiple individuals with different knowledge can find their way through a maze more efficiently, this synergy allows for a more comprehensive understanding of complex issues and can lead to more reliable predictions.
Lastly, teams that employ simpler models and leverage past data typically outperform those that do not. By focusing on essential factors and grounding predictions in historical trends, these teams can illuminate the most promising paths through the intricate labyrinth of challenges we face.
In conclusion, polymathic collectives such as the Grey Swan Guild demonstrate the value of bringing together diverse perspectives to tackle the complex maze of modern challenges. By fostering collaboration among experts from different domains and emphasizing data-driven, simple models, we can improve the accuracy of predictions and make more informed decisions about our collective future.
Source: The Conversation
[https://theconversation.com/the-limits-of-expert-judgment-lessons-from-social-science-forecasting-during-the-pandemic-201130]
