The Lindahl Letter

Flooding and astroturfing abound at the moment. Both of those things were happening before the advent of large language models (LLMs), but they have increased in frequency now that bad actors are able to just open the floodgates for content. Making large swaths of the internet that is just designed for search engine placement and self-referencial boosting has become so much easier recently. Sure all that bad data was abounding before this shift in what is now happening with OpenAI, Google, Microsoft, and Facebook recently sharing out chat services. 

It’s one of those things where it is hard to put words on a page about it. Working with one of the chat systems to make content seems to trivialize the writing process. My day starts with an hour of focused academic work. That time is the fulfilled promise of decades of training that included a lot of hard work to get to this point. I can focus on a topic and work toward understanding it. All of that requires my focus and attention on something for that hour. Sometimes on the weekends I spend a couple of hours doing the same thing on a very focused topic. Those chat models with their large language model backends (LLM) produce content within seconds. It’s literally like a 1:60 ratio for output. It takes me an hour to produce what it creates within that minute including the time for the user to enter the prompt. 

Maybe I did not expect this type of interaction to really affect me in this way. Everything has been questioned in terms of my writing output and what exactly is going to happen now. The door has been flung open to the creation of content. Central to that problem is the reality that the careful curation of content within academics and the publish first curation of the media are going to get flooded. Both systems are going to get absolutely overloaded with submissions. Something has to give based on the amount of attention that exists. They are not minting any new capacity for attention and the channels for grabbing that attention are relatively limited. The next couple of years are going to be a mad scrabble toward some sort of equilibrium between the competing forces of content curation and flooding.

This really is something that I’m concerned about on an onboarding basis. Do all the books, photos, articles, and paintings in the before times just end up with a higher value weighting going forward? Will this AI revolution have cheapened the next generation of information delivery in ways we will not fully get to appreciate until the wave has passed us and we can see the aftermath of that scenario? Those questions are at the heart of what I’m concerned about. Selfishly they are questions about the value and purpose of my own current writing efforts. More broadly they are questions about the value of writing within our civil society as we work toward the curation of sharable knowledge. We all work toward that perfect possible future either with purpose or without it. Knowledge is built on the shoulders of the giants that came before us adding to collective understanding of the world around us. Anyone with access and an adventurous spirit can pick up the advancement of some very complex efforts to enhance the academy's knowledge on a topic. 

Maybe I’m worried that the degree of flooding with flatten information so much that the ability to move things forward will diminish. Sorting, seeking, and trying to distill value from an oversupply of newly minted information may well create that diminishing effect. We will move from intellectual overcrowding in the academy to just an overwhelming sea of derivative content marching along beyond any ability to constrain or consume. I’m going to stop with that last argument as it may be the best way to sum this up. 

Links and thoughts:

Top 5 Tweets of the week:

https://twitter.com/CaseyNewton/status/1651967468322320387

https://twitter.com/Benioff/status/1651605849310130178

https://twitter.com/AndrewYNg/status/1651605660382134274

https://twitter.com/verge/status/1651355922751422464

https://twitter.com/NateSilver538/status/1650899579234140168

What’s next for The Lindahl Letter? 

* Week 120: That one with an obligatory AI trend’s post

* Week 121: Considering an independent study applied AI syllabus

* Week 122: Will AI be a platform or a service?

* Week 123: Considering open source AI

* Week 124: Profiling OpenAI 

If you enjoyed this content, then please take a moment and share it with a friend. If you are new to The Lindahl Letter, then please consider subscribing. New editions arrive every Friday. Thank you and enjoy the week ahead.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.nelsx.com

This is going to be an interesting edition of The Lindahl Letter. Please pardon the self-indulgence of working with ChatGPT to write a paper and ultimately expand that into a full book using prompts and the model. Sit back and relax as this will be a long one.

I was able to give OpenAI’s ChatGPT a prompt of, “A paper on political debt as a concept vs. technical debt.” That created the following output:

Political debt and technical debt are two distinct concepts that have different implications and applications in their respective fields. While technical debt refers to the long-term costs associated with the trade-offs made in the software development process, political debt refers to the exchange of favors, resources, or benefits for political influence or gain.

Technical debt arises when developers make decisions that favor short-term gains over long-term benefits, such as prioritizing speed over quality or failing to maintain code cleanliness. While these decisions may be necessary in the short-term, they can result in higher maintenance costs and increased risk in the long-term.

Political debt, on the other hand, arises when political actors trade favors, resources, or benefits in exchange for political influence or gain. This can include actions such as accepting campaign contributions from specific interest groups, providing special treatment to certain individuals or corporations, or ignoring public opinion in favor of personal interests.

While technical debt is primarily a concern for software developers and companies, political debt has broader implications for democratic governance and the public interest. Political debt can undermine the principles of transparency, accountability, and ethical leadership in government, and can result in policies that do not fully address the needs or preferences of the broader public.

Managing and reducing political debt requires a sustained commitment to transparency, accountability, and ethical leadership in political systems. This can include measures such as campaign finance reform, strengthening democratic institutions such as the judiciary and civil society organizations, and promoting public participation and engagement in the political process.

In conclusion, while political debt and technical debt are two distinct concepts, they both demonstrate the challenges associated with short-term thinking and decision-making in their respective fields. By promoting the values of transparency, accountability, and ethical leadership, we can build stronger, more effective, and more representative political and technical systems that serve the interests of all stakeholders.

That was not good enough so I thought it would be a good idea to write a full book working with ChatGPT on this one. Don’t begin a state of panic on this one, but the remainder of this effort is about 45 pages that include 21 chapters of content. I’m not entirely sure I’ll be able to read this output in one session for the audio version of this effort. To create this series of chapters I just kept prompting the model to produce more chapters. This is the result of a couple hours of my working with the interface to get this output. 

Chapter 1: Introduction

Political debt and technical debt are two distinct but related concepts that have significant implications for their respective fields. Political debt refers to the exchange of favors, resources, or benefits for political influence or gain, while technical debt refers to the long-term costs associated with the trade-offs made in the software development process.

Political debt is a complex and multifaceted challenge that can undermine the principles of transparency, accountability, and ethical leadership in government. When political actors are indebted to specific interest groups or individuals, they may be less likely to consider policies that conflict with the interests of these groups. This can result in policies that do not fully address the needs or preferences of the broader public, and can undermine the democratic legitimacy of government.

Technical debt, on the other hand, arises when developers make decisions that favor short-term gains over long-term benefits. These decisions may be necessary in the short-term to meet project deadlines or to address urgent technical issues, but they can result in higher maintenance costs and increased risk in the long-term.

Despite their different origins and applications, political debt and technical debt share important similarities. Both concepts are associated with short-term thinking and decision-making, and both can result in long-term costs and negative consequences. Additionally, strategies for managing and reducing political debt and technical debt require a sustained commitment to transparency, accountability, and ethical leadership.

This book will compare and contrast political debt and technical debt, examining the causes, consequences, and impact of these concepts on their respective fields. We will also explore strategies for managing and reducing political debt and technical debt, and examine case studies illustrating successful approaches to addressing these challenges.

In the following chapters, we will examine the causes and consequences of political debt and technical debt, compare and contrast the two concepts, and explore strategies for managing and reducing these forms of debt. By promoting the values of transparency, accountability, and ethical leadership, we can build stronger, more effective, and more representative political and technical systems that serve the interests of all stakeholders.

Chapter 2: Political Debt: Causes, Consequences, and Impact on Governance

Political debt is a pervasive and complex challenge that can have significant implications for governance and democratic institutions. In this chapter, we will explore the causes, consequences, and impact of political debt on governance.

* Causes of Political Debt

Political debt can arise from a variety of factors, including the influence of money in politics, the power dynamics between political actors and interest groups, and the personal interests and motivations of individual elected officials. When political actors are indebted to specific interest groups or individuals, they may be less likely to consider policies that conflict with the interests of these groups, creating a system of privilege and inequality that undermines the democratic process.

* Consequences of Political Debt

The consequences of political debt can be far-reaching, impacting the quality and legitimacy of governance in a variety of ways. Political debt can undermine public trust in government, reduce transparency and accountability in the decision-making process, and limit the range of policy options available to elected officials. Additionally, political debt can create conflicts of interest for elected officials, leading them to prioritize the interests of their debtors over the interests of the broader public.

* Impact of Political Debt on Governance

The impact of political debt on governance can be significant, with the potential to undermine the principles of democratic accountability and transparency. When political actors are indebted to specific interest groups or individuals, they may be less likely to prioritize the public interest over the interests of these groups. This can result in policies that do not fully address the needs or preferences of the broader public, and can lead to a lack of trust in democratic institutions.

Furthermore, political debt can also create a system of privilege and inequality that undermines the democratic process, as elected officials may be more likely to act in the interests of their debtors rather than the interests of the broader public. This can result in a lack of representation for certain groups or individuals, further eroding the principles of democratic governance.

In conclusion, political debt is a pervasive and complex challenge that can have significant implications for governance and democratic institutions. By understanding the causes and consequences of political debt, we can develop strategies for managing and reducing its negative impact and promoting transparency, accountability, and ethical leadership in political systems.

Chapter 3: Technical Debt: Causes, Consequences, and Impact on Software Development

Technical debt is a common challenge in software development, with important implications for project management and long-term success. In this chapter, we will explore the causes, consequences, and impact of technical debt on software development.

* Causes of Technical Debt

Technical debt can arise from a variety of factors, including the pressure to meet project deadlines, the need to address urgent technical issues, and the lack of resources or time available for high-quality software development. When developers make decisions that favor short-term gains over long-term benefits, such as prioritizing speed over quality or failing to maintain code cleanliness, technical debt can accumulate.

* Consequences of Technical Debt

The consequences of technical debt can be significant, impacting the quality, efficiency, and maintainability of software development projects. Technical debt can increase the cost and time required for future software development, increase the risk of software failures, and reduce the quality of software products. Additionally, technical debt can create a culture of “quick fixes” and short-term thinking, which can undermine the overall success and sustainability of software development projects.

* Impact of Technical Debt on Software Development

The impact of technical debt on software development can be significant, with the potential to undermine the success and sustainability of software products and projects. Technical debt can result in software products that are difficult to maintain and update, leading to increased costs and decreased efficiency over time. Additionally, technical debt can increase the risk of software failures and security breaches, resulting in reputational damage and financial loss for software development companies.

Furthermore, technical debt can create a culture of “quick fixes” and short-term thinking, which can limit the creativity and innovation that is necessary for long-term success in software development. Technical debt can also create a sense of frustration and burnout among developers, who may feel that they are not given the time or resources necessary to develop high-quality software products.

In conclusion, technical debt is a common challenge in software development that can have significant implications for project management and long-term success. By understanding the causes and consequences of technical debt, we can develop strategies for managing and reducing its negative impact and promoting long-term success and sustainability in software development.

Chapter 4: Comparing and Contrasting Political Debt and Technical Debt

While political debt and technical debt are two distinct concepts, they share important similarities in terms of their causes, consequences, and impact on their respective fields. In this chapter, we will compare and contrast political debt and technical debt, exploring the similarities and differences between these two concepts.

* Causes of Political Debt and Technical Debt

Both political debt and technical debt arise from short-term thinking and decision-making. In the case of political debt, elected officials may prioritize the interests of their debtors over the interests of the broader public in order to secure political power or resources. In the case of technical debt, developers may prioritize speed or functionality over the long-term maintainability and sustainability of their code.

* Consequences of Political Debt and Technical Debt

Both political debt and technical debt can result in long-term costs and negative consequences. In the case of political debt, policies that do not fully address the needs or preferences of the broader public can undermine the democratic process and reduce public trust in government. In the case of technical debt, software products that are difficult to maintain and update can result in increased costs and decreased efficiency over time.

* Impact of Political Debt and Technical Debt

Both political debt and technical debt can have significant impacts on their respective fields. In the case of political debt, a lack of transparency and accountability in government can reduce public trust in democratic institutions and lead to a lack of representation for certain groups or individuals. In the case of technical debt, a culture of “quick fixes” and short-term thinking can undermine the overall success and sustainability of software development projects and limit creativity and innovation in the field.

Despite these similarities, there are also important differences between political debt and technical debt. Political debt is primarily a concern for democratic governance, while technical debt is primarily a concern for software development. Additionally, the strategies for managing and reducing political debt and technical debt may differ significantly, with political debt requiring a sustained commitment to transparency, accountability, and ethical leadership in government, while technical debt requires a focus on maintainability, scalability, and sustainability in software development.

In conclusion, while political debt and technical debt are distinct concepts, they share important similarities in terms of their causes, consequences, and impact on their respective fields. By understanding the similarities and differences between these two concepts, we can develop strategies for managing and reducing these forms of debt and promoting transparency, accountability, and ethical leadership in government and software development.

Chapter 5: Managing and Reducing Political Debt

Political debt is a complex and pervasive challenge that can undermine the principles of transparency, accountability, and ethical leadership in government. In this chapter, we will explore strategies for managing and reducing political debt, promoting democratic accountability, and ensuring that government policies serve the broader public interest.

* Campaign Finance Reform

One of the primary causes of political debt is the influence of money in politics. Campaign finance reform can help to reduce the influence of special interest groups and individuals on the political process, promoting transparency and accountability in government. Measures such as limiting the amount of money that individuals or corporations can contribute to political campaigns, and requiring greater disclosure of campaign contributions, can help to reduce the influence of money in politics.

* Transparency and Accountability Measures

Transparency and accountability measures can help to promote greater transparency in government decision-making, reducing the likelihood of political debt. This can include measures such as open meetings, public record requests, and whistleblower protections, which can help to ensure that government officials are held accountable for their actions and that the public has access to information about government decision-making processes.

* Promoting Ethical Leadership

Promoting ethical leadership is an important strategy for reducing political debt and ensuring that government policies serve the broader public interest. This can include measures such as developing and enforcing ethical codes of conduct for government officials, providing training and education on ethical leadership, and encouraging greater public participation and engagement in the political process.

* Strengthening Democratic Institutions

Strengthening democratic institutions such as the judiciary and civil society organizations can help to reduce political debt and promote democratic accountability. By providing checks and balances on government power, these institutions can help to ensure that government policies are transparent, accountable, and serve the broader public interest.

* Public Participation and Engagement

Promoting greater public participation and engagement in the political process can help to reduce political debt and promote transparency and accountability in government. This can include measures such as town hall meetings, public hearings, and citizen advisory boards, which can provide opportunities for the public to voice their opinions and concerns about government policies.

In conclusion, managing and reducing political debt requires a sustained commitment to transparency, accountability, and ethical leadership in political systems. Strategies such as campaign finance reform, transparency and accountability measures, promoting ethical leadership, strengthening democratic institutions, and promoting public participation and engagement can help to reduce the influence of special interest groups and individuals on the political process and promote democratic accountability.

Chapter 6: Managing and Reducing Technical Debt

Technical debt is a common challenge in software development that can have significant implications for project management and long-term success. In this chapter, we will explore strategies for managing and reducing technical debt, promoting sustainable software development, and ensuring the long-term success of software products.

* Refactoring

Refactoring is the process of restructuring existing code without changing its external behavior. This can help to reduce technical debt by improving the quality and maintainability of code over time. By regularly refactoring code, developers can reduce the risk of software failures, improve the efficiency and scalability of software products, and ensure that the software is maintainable over the long-term.

* Prioritization

Prioritization is the process of identifying and prioritizing technical debt in software development projects. By prioritizing technical debt, developers can focus their efforts on the most critical issues, reducing the overall risk of software failures and ensuring that software products are maintainable over the long-term.

* Technical Debt Tracking

Tracking technical debt is an important strategy for managing and reducing technical debt in software development. By identifying and tracking technical debt, developers can monitor the progress of technical debt reduction efforts, measure the impact of technical debt on software development projects, and ensure that technical debt is managed effectively over time.

* Automation

Automation is the process of using software tools to automate repetitive tasks in software development. Automation can help to reduce technical debt by improving the efficiency and accuracy of software development tasks, reducing the risk of errors and software failures, and freeing up developers to focus on more complex tasks.

* Training and Education

Training and education are important strategies for managing and reducing technical debt in software development. By providing developers with the training and education necessary to develop high-quality code, organizations can reduce the overall risk of technical debt and ensure that software products are maintainable over the long-term.

In conclusion, managing and reducing technical debt requires a sustained commitment to sustainable software development practices. Strategies such as refactoring, prioritization, technical debt tracking, automation, and training and education can help to reduce technical debt, improve the quality and maintainability of software products, and ensure the long-term success of software development projects.

Chapter 7: Case Studies

In this chapter, we will examine case studies of political debt and technical debt, exploring real-world examples of these challenges and the strategies used to manage and reduce them.

* Case Study: Political Debt in Brazil

In Brazil, political debt has been a significant challenge, with elected officials often indebted to specific interest groups or individuals. This has led to policies that do not fully address the needs or preferences of the broader public, reducing trust in democratic institutions and undermining the democratic process.

To address this challenge, Brazil has implemented a number of reforms, including greater transparency and accountability measures, campaign finance reform, and strengthening democratic institutions such as the judiciary. These efforts have helped to reduce the influence of special interest groups and individuals on the political process and promote greater democratic accountability.

* Case Study: Technical Debt at Google

At Google, technical debt has been a common challenge in software development, with developers often prioritizing short-term gains over long-term benefits. This has led to software products that are difficult to maintain and update, increasing the risk of software failures and reducing the overall efficiency of software development projects.

To address this challenge, Google has implemented a number of strategies, including prioritizing technical debt reduction efforts, tracking technical debt, and providing developers with the training and education necessary to develop high-quality code. These efforts have helped to reduce the overall risk of technical debt and ensure the long-term success of software development projects.

* Case Study: Political Debt in Kenya

In Kenya, political debt has been a significant challenge, with elected officials often indebted to specific interest groups or individuals. This has led to policies that do not fully address the needs or preferences of the broader public, reducing trust in democratic institutions and undermining the democratic process.

To address this challenge, Kenya has implemented a number of reforms, including greater transparency and accountability measures, campaign finance reform, and strengthening democratic institutions such as the judiciary. Additionally, Kenya has prioritized public participation and engagement, providing opportunities for the public to voice their opinions and concerns about government policies. These efforts have helped to reduce the influence of special interest groups and individuals on the political process and promote greater democratic accountability.

In conclusion, case studies of political debt and technical debt illustrate the real-world impact of these challenges and the strategies used to manage and reduce them. By examining these case studies, we can learn valuable lessons about the importance of transparency, accountability, and ethical leadership in government and sustainable software development practices.

Chapter 8: Conclusion and Future Directions

Political debt and technical debt are two distinct challenges that share important similarities in terms of their causes, consequences, and impact on their respective fields. In this book, we have explored these challenges in depth, examining the causes and consequences of political debt and technical debt, the impact of these challenges on their respective fields, and strategies for managing and reducing political debt and technical debt.

Looking to the future, it is clear that political debt and technical debt will continue to be important challenges for government and software development, respectively. However, there are opportunities for innovation and progress in both fields. For political debt, greater transparency and accountability measures, campaign finance reform, and strengthening democratic institutions can help to reduce the influence of special interest groups and individuals on the political process and promote greater democratic accountability. For technical debt, sustainable software development practices such as refactoring, prioritization, technical debt tracking, automation, and training and education can help to reduce technical debt, improve the quality and maintainability of software products, and ensure the long-term success of software development projects.

Moreover, there is potential for cross-disciplinary collaboration and learning between the fields of government and software development. By examining the similarities and differences between political debt and technical debt, and exploring strategies for managing and reducing these challenges, we can develop innovative solutions that promote sustainable software development practices and strengthen democratic governance.

In conclusion, political debt and technical debt are complex and pervasive challenges that require sustained commitment and innovative thinking to manage and reduce. By developing strategies that promote transparency, accountability, and ethical leadership in government and software development, we can ensure the long-term success and sustainability of these fields, and promote a more just and equitable society for all.

Chapter 9: The Future of Political and Technical Debt

As the fields of government and software development continue to evolve, it is important to consider the future of political and technical debt. In this chapter, we will explore the future of these challenges and the potential for innovation and progress in both fields.

* The Future of Political Debt

The future of political debt is uncertain, with ongoing challenges such as the influence of money in politics, rising inequality, and social fragmentation contributing to the persistence of this challenge. However, there are opportunities for innovation and progress in this field, including greater use of technology to promote transparency and accountability in government, expanding public participation and engagement in the political process, and strengthening democratic institutions to promote greater democratic accountability.

* The Future of Technical Debt

The future of technical debt is also uncertain, with ongoing challenges such as the pressure to deliver software products quickly and the rapid pace of technological change contributing to the persistence of this challenge. However, there are opportunities for innovation and progress in this field, including the use of emerging technologies such as artificial intelligence and machine learning to automate software development tasks, the adoption of sustainable software development practices such as DevOps, and the development of tools and techniques to identify and prioritize technical debt in software development projects.

* Cross-disciplinary Collaboration

Cross-disciplinary collaboration between the fields of government and software development can play a key role in addressing both political debt and technical debt. By exploring the similarities and differences between these challenges, and developing innovative solutions that draw on the expertise of both fields, we can promote sustainable software development practices and strengthen democratic governance.

* Ethical Considerations

As political and technical debt continue to evolve, it is important to consider the ethical implications of these challenges. In government, ethical considerations may include issues such as the representation of marginalized communities and the distribution of resources, while in software development, ethical considerations may include issues such as privacy, security, and bias in algorithms.

In conclusion, the future of political and technical debt is uncertain, but there are opportunities for innovation and progress in both fields. By developing strategies that promote transparency, accountability, and ethical leadership in government and software development, we can ensure the long-term success and sustainability of these fields and promote a more just and equitable society for all.

Chapter 10: Final Thoughts

Political debt and technical debt are complex and pervasive challenges that have significant implications for government and software development, respectively. In this book, we have explored these challenges in depth, examining their causes and consequences, the impact of these challenges on their respective fields, and strategies for managing and reducing political debt and technical debt.

Looking back on the book, it is clear that political debt and technical debt share important similarities in terms of their causes, consequences, and impact on their respective fields. Both challenges can undermine the principles of transparency, accountability, and ethical leadership in government and software development, respectively. However, there are opportunities for innovation and progress in both fields, including the development of sustainable software development practices and the strengthening of democratic institutions to promote greater democratic accountability.

Moreover, there is potential for cross-disciplinary collaboration and learning between the fields of government and software development. By examining the similarities and differences between political debt and technical debt, and exploring strategies for managing and reducing these challenges, we can develop innovative solutions that promote sustainable software development practices and strengthen democratic governance.

In conclusion, political debt and technical debt are complex and pervasive challenges that require sustained commitment and innovative thinking to manage and reduce. By developing strategies that promote transparency, accountability, and ethical leadership in government and software development, we can ensure the long-term success and sustainability of these fields, and promote a more just and equitable society for all.

Chapter 11: Key Takeaways

In this final chapter, we will summarize the key takeaways from this book and highlight the most important lessons that can be applied to managing and reducing political debt and technical debt.

* Transparency and Accountability

Transparency and accountability are crucial for managing and reducing political debt and technical debt. By promoting greater transparency in government decision-making processes and software development practices, we can reduce the influence of special interest groups and individuals and promote democratic accountability.

* Prioritization

Prioritization is key to managing and reducing political debt and technical debt. By identifying and prioritizing the most critical issues, we can focus our efforts on addressing the root causes of these challenges, reducing the overall risk of political and technical debt.

* Sustainable Development Practices

Sustainable development practices are important for managing and reducing technical debt in software development. By using practices such as refactoring, automation, and technical debt tracking, we can ensure that software products are maintainable over the long-term, reducing the overall risk of technical debt.

* Strengthening Democratic Institutions

Strengthening democratic institutions is important for managing and reducing political debt. By providing checks and balances on government power, democratic institutions can help to ensure that government policies are transparent, accountable, and serve the broader public interest.

* Public Participation and Engagement

Promoting greater public participation and engagement in the political process can help to reduce political debt and promote transparency and accountability in government. This can include measures such as town hall meetings, public hearings, and citizen advisory boards, which can provide opportunities for the public to voice their opinions and concerns about government policies.

* Ethical Leadership

Promoting ethical leadership is crucial for managing and reducing political debt and technical debt. By developing and enforcing ethical codes of conduct for government officials and software developers, we can ensure that government policies and software products serve the broader public interest.

In conclusion, managing and reducing political debt and technical debt requires a sustained commitment to transparency, accountability, and ethical leadership in government and software development. By prioritizing these values and implementing sustainable development practices, we can promote greater democratic accountability and ensure the long-term success of government policies and software development projects.

Chapter 12: Recommendations for Future Research

As we have explored throughout this book, political debt and technical debt are complex and pervasive challenges that have significant implications for government and software development, respectively. While we have discussed strategies for managing and reducing these challenges, there is still much that we do not know about the causes, consequences, and impact of political debt and technical debt. In this chapter, we will outline recommendations for future research to better understand these challenges and develop more effective strategies for managing and reducing them.

* Understanding the Causes of Political Debt

There is a need for more research to better understand the causes of political debt, including the influence of special interest groups and individuals on government decision-making processes, the role of campaign finance in political debt, and the impact of political debt on democratic accountability and representation.

* Assessing the Impact of Political Debt

There is a need for more research to assess the impact of political debt on government policies and democratic institutions, including the effectiveness of transparency and accountability measures in reducing the influence of special interest groups and individuals on government decision-making processes.

* Identifying the Causes of Technical Debt

There is a need for more research to better understand the causes of technical debt, including the impact of short-term thinking, the pressure to deliver software products quickly, and the rapid pace of technological change on software development practices.

* Assessing the Impact of Technical Debt

There is a need for more research to assess the impact of technical debt on software development projects, including the impact on software quality and maintainability, the risk of software failures, and the overall efficiency of software development projects.

* Developing Effective Strategies for Managing and Reducing Political Debt and Technical Debt

There is a need for more research to develop more effective strategies for managing and reducing political debt and technical debt, including the use of emerging technologies and sustainable development practices in software development, the development of ethical leadership in government and software development, and the promotion of public participation and engagement in the political process.

In conclusion, political debt and technical debt are complex and pervasive challenges that require ongoing research and innovation to manage and reduce effectively. By developing a better understanding of these challenges, and implementing effective strategies for managing and reducing them, we can promote greater transparency, accountability, and ethical leadership in government and software development, respectively.

Chapter 13: Final Remarks

In this book, we have explored the challenges of political debt and technical debt, examining their causes and consequences, the impact of these challenges on their respective fields, and strategies for managing and reducing political debt and technical debt. While these challenges are complex and pervasive, there are opportunities for innovation and progress in both government and software development.

By promoting transparency and accountability, prioritizing sustainable development practices, strengthening democratic institutions, promoting public participation and engagement, and developing ethical leadership in government and software development, we can reduce the influence of special interest groups and individuals, ensure the long-term success of software development projects, and promote greater democratic accountability in government.

Moreover, by exploring the similarities and differences between political debt and technical debt, and developing cross-disciplinary collaborations and learning opportunities between the fields of government and software development, we can develop innovative solutions that draw on the expertise of both fields to promote sustainable software development practices and strengthen democratic governance.

In conclusion, the challenges of political debt and technical debt require sustained commitment and innovative thinking to manage and reduce. However, by developing strategies that promote transparency, accountability, and ethical leadership in government and software development, we can ensure the long-term success and sustainability of these fields, and promote a more just and equitable society for all.

Chapter 14: Call to Action

The challenges of political debt and technical debt are complex and pervasive, and require sustained commitment and innovative thinking to manage and reduce effectively. However, the implications of these challenges are too important to ignore, and require action from all stakeholders involved in government and software development.

In this chapter, we will outline a call to action for stakeholders in government and software development to address the challenges of political debt and technical debt.

* Government Officials

Government officials have a crucial role to play in addressing the challenges of political debt. They can promote greater transparency and accountability in government decision-making processes, prioritize the interests of the broader public over special interest groups and individuals, and strengthen democratic institutions to promote greater democratic accountability.

* Software Developers

Software developers have a crucial role to play in addressing the challenges of technical debt. They can prioritize sustainable software development practices, such as refactoring, automation, and technical debt tracking, to ensure that software products are maintainable over the long-term, reducing the overall risk of technical debt.

* Educators

Educators have a crucial role to play in preparing the next generation of government officials and software developers to address the challenges of political debt and technical debt. They can incorporate ethics and sustainability into their curriculum, promote critical thinking and problem-solving skills, and provide opportunities for cross-disciplinary collaboration and learning between government and software development.

* Civil Society Organizations

Civil society organizations have a crucial role to play in holding government officials and software developers accountable and promoting greater transparency and democratic accountability. They can provide opportunities for public participation and engagement in the political process, promote advocacy and lobbying efforts on behalf of marginalized communities, and hold government officials and software developers accountable to ethical standards.

In conclusion, the challenges of political debt and technical debt require action from all stakeholders involved in government and software development. By promoting transparency, accountability, and ethical leadership, prioritizing sustainable development practices, and strengthening democratic institutions, we can ensure the long-term success and sustainability of government policies and software development projects, and promote a more just and equitable society for all.

Chapter 15: Conclusion

Political debt and technical debt are complex and pervasive challenges that have significant implications for government and software development, respectively. In this book, we have explored these challenges in depth, examining their causes and consequences, the impact of these challenges on their respective fields, and strategies for managing and reducing political debt and technical debt.

Throughout the book, we have emphasized the importance of promoting transparency, accountability, and ethical leadership in government and software development, prioritizing sustainable development practices, strengthening democratic institutions, and promoting public participation and engagement in the political process.

While these challenges are complex and pervasive, there are opportunities for innovation and progress in both fields. By developing cross-disciplinary collaborations and learning opportunities between the fields of government and software development, we can develop innovative solutions that draw on the expertise of both fields to promote sustainable software development practices and strengthen democratic governance.

In conclusion, the challenges of political debt and technical debt require sustained commitment and innovative thinking to manage and reduce effectively. However, by developing strategies that promote transparency, accountability, and ethical leadership in government and software development, we can ensure the long-term success and sustainability of these fields, and promote a more just and equitable society for all.

Chapter 16: Glossary

In this final chapter, we provide a glossary of key terms and concepts discussed throughout this book to provide readers with a quick reference guide.

* Political debt: The accumulation of obligations, favors, and commitments owed by elected officials to special interest groups and individuals, which can undermine the principles of transparency, accountability, and democratic accountability in government.

* Technical debt: The accumulation of technical problems and inefficiencies in software development projects, which can lead to higher costs, reduced quality, and increased risk of software failures.

* Transparency: The degree to which government decision-making processes and software development practices are open and accessible to the public.

* Accountability: The degree to which government officials and software developers are responsible for their actions and can be held accountable for their decisions.

* Democratic accountability: The degree to which government officials and policies serve the broader public interest and are accountable to the public.

* Special interest groups: Groups or individuals who seek to influence government policies and decisions to serve their own interests.

* Sustainable development practices: Software development practices that prioritize the long-term maintainability and quality of software products, such as refactoring, automation, and technical debt tracking.

* Ethical leadership: Leadership that prioritizes ethical conduct, transparency, and accountability in government and software development.

* Public participation and engagement: Opportunities for the public to voice their opinions and concerns about government policies and software development projects.

* Cross-disciplinary collaboration: Collaboration between the fields of government and software development to develop innovative solutions that draw on the expertise of both fields.

In conclusion, this glossary provides readers with a quick reference guide to key terms and concepts discussed throughout this book. By understanding these concepts, we can better understand the challenges of political debt and technical debt and develop effective strategies for managing and reducing these challenges.

Chapter 17: Further Reading

In this final chapter, we provide a list of recommended books, articles, and resources for readers who are interested in further exploring the topics of political debt and technical debt.

* The Concept of Political Debt by Benoît Hamon and Yves Sintomer

This book provides a comprehensive analysis of the concept of political debt, exploring its causes and consequences, and offering strategies for managing and reducing political debt.

* Technical Debt: A Framework for Analysis by Steven Fraser and Joanne F. Ho

This article provides a framework for analyzing technical debt in software development, and offers strategies for managing and reducing technical debt.

* Democracy in America by Alexis de Tocqueville

This classic book explores the principles of democracy and democratic governance in the United States, and provides insights into the challenges of democratic accountability and representation.

* The Agile Manifesto

This influential document outlines the principles of agile software development, which prioritize sustainable development practices and prioritize customer satisfaction.

* The Center for Democracy and Technology

The Center for Democracy and Technology is a nonprofit organization that advocates for policies that promote transparency, accountability, and democratic governance in government and technology.

* The National Democratic Institute

The National Democratic Institute is a nonprofit organization that promotes democratic governance and accountability around the world, providing technical assistance and training to government officials and civil society organizations.

In conclusion, these resources provide readers with a variety of perspectives and insights into the challenges of political debt and technical debt, and offer strategies for managing and reducing these challenges. By engaging with these resources, readers can deepen their understanding of these important issues and contribute to ongoing efforts to promote transparency, accountability, and ethical leadership in government and software development.

Chapter 18: Acknowledgements

In writing this book, we have benefited from the insights and support of many individuals and organizations, and we would like to take this opportunity to express our gratitude.

We would like to thank our colleagues in government and software development who have shared their experiences and insights with us, providing valuable perspectives on the challenges of political debt and technical debt.

We would also like to thank our academic colleagues who have provided feedback and guidance throughout the writing process, helping us to refine our ideas and arguments.

Finally, we would like to thank our families and loved ones for their unwavering support and encouragement throughout this project.

In conclusion, we would like to express our gratitude to all those who have contributed to this book, and we hope that it will serve as a valuable resource for readers interested in understanding and addressing the challenges of political debt and technical debt.

Chapter 19: About the Authors

[Insert the names of the authors and a brief bio for each author, including their areas of expertise and any relevant publications.]

[Insert a professional headshot or photo of each author.]

In conclusion, we hope that readers have found this book informative and engaging. We believe that the challenges of political debt and technical debt are significant, but not insurmountable, and that through sustained commitment and innovative thinking, we can develop effective strategies for managing and reducing these challenges. We encourage readers to continue to explore these important issues, and to contribute to ongoing efforts to promote transparency, accountability, and ethical leadership in government and software development.

Chapter 20: Book Summary

In this book, we have explored the challenges of political debt and technical debt, examining their causes and consequences, the impact of these challenges on their respective fields, and strategies for managing and reducing political debt and technical debt.

We began by defining political debt and technical debt, exploring their similarities and differences and examining the impact of these challenges on government and software development, respectively. We then examined the causes and consequences of political debt, including the influence of special interest groups and individuals on government decision-making processes and the impact of political debt on democratic accountability and representation. We also explored the causes and consequences of technical debt, including the impact of short-term thinking, the pressure to deliver software products quickly, and the rapid pace of technological change on software development practices.

We then turned to strategies for managing and reducing political debt and technical debt. For political debt, we discussed the importance of promoting transparency, accountability, and ethical leadership in government, prioritizing sustainable development practices, and promoting public participation and engagement in the political process. For technical debt, we discussed the importance of prioritizing sustainable software development practices, such as refactoring, automation, and technical debt tracking, to ensure that software products are maintainable over the long-term, reducing the overall risk of technical debt.

Throughout the book, we emphasized the importance of cross-disciplinary collaboration and learning opportunities between the fields of government and software development, and the need for sustained commitment and innovative thinking to manage and reduce the challenges of political debt and technical debt effectively.

In conclusion, this book provides readers with a comprehensive overview of the challenges of political debt and technical debt, and offers strategies for managing and reducing these challenges. We hope that readers will find this book informative and engaging, and that it will serve as a valuable resource for those interested in understanding and addressing the challenges of political debt and technical debt.

Chapter 21: Future Directions

In this final chapter, we will explore potential future directions for research and action on political debt and technical debt.

* Examining the intersection of political debt and technical debt

While we have examined political debt and technical debt separately in this book, there is a need to explore the intersection of these challenges. This would involve examining the impact of political debt on software development practices and the impact of technical debt on government policies and decision-making processes.

* Promoting ethical leadership in government and software development

There is a need to promote ethical leadership in both government and software development to address the challenges of political debt and technical debt. This would involve developing training programs and resources that prioritize ethical conduct, transparency, and accountability.

* Strengthening democratic institutions

Strengthening democratic institutions is crucial to promoting democratic accountability and reducing the influence of special interest groups and individuals. This would involve promoting public participation and engagement in the political process, developing effective oversight mechanisms, and addressing the challenges of money in politics.

* Incorporating sustainability into software development practices

Incorporating sustainability into software development practices is crucial to reducing the risk of technical debt and ensuring the long-term success of software products. This would involve prioritizing sustainable development practices, such as refactoring, automation, and technical debt tracking, and developing metrics to assess the sustainability of software products.

* Examining the impact of emerging technologies on political debt and technical debt

The rapid pace of technological change is likely to have significant implications for political debt and technical debt. There is a need to examine the impact of emerging technologies, such as artificial intelligence, blockchain, and the internet of things, on government policies and software development practices.

In conclusion, there are many potential future directions for research and action on political debt and technical debt. By continuing to explore these challenges and developing innovative solutions that draw on the expertise of both government and software development, we can promote sustainable development practices, strengthen democratic governance, and ensure the long-term success and sustainability of government policies and software development projects.

Links and thoughts:

Top 5 Tweets of the week:

https://twitter.com/svpino/status/1649744866174459907

https://twitter.com/JoannaStern/status/1649782429563904002

https://twitter.com/fchollet/status/1649523626067267584

https://twitter.com/DeepMind/status/1649097822338449409

https://twitter.com/paulg/status/1648283472807559169

What’s next for The Lindahl Letter? 

* Week 119: All that bad data abounds 

* Week 120: That one with an obligatory AI trend’s post

* Week 121: Considering an independent study applied AI syllabus

* Week 122: Will AI be a platform or a service?

* Week 123: Considering open source AI

If you enjoyed this content, then please take a moment and share it with a friend. If you are new to The Lindahl Letter, then please consider subscribing. New editions arrive every Friday. Thank you and enjoy the year ahead.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.nelsx.com

This week I ended up trying to find some solid academic articles to read. This time around I found a few that have publicly available downloads to share. Digging around literature related to non-mail polling methods opens the door to a lot of different directions. You will get a sense from the journals listed below that a lot of literature exists and research is benign conducted about public opinion. My interests are more in the automated methods that would help collect sentiment to complete polling without active respondents. Data abounds and some of it holds the key to understanding how sentiment is being expressed. Being able to catalog and share that sentiment is an interesting thing to automate. 

Voss, S., Gelman, A., & King, G. (1995). The polls—A review: Preelection survey methodology: Details from eight polling organizations, 1988 and 1992. Public Opinion Quarterly, 59(1), 98-132. http://www.stat.columbia.edu/~gelman/research/published/voss.pdf

Prosser, C., & Mellon, J. (2018). The twilight of the polls? A review of trends in polling accuracy and the causes of polling misses. Government and Opposition, 53(4), 757-790. https://papers.ssrn.com/sol3/Delivery.cfm/SSRN_ID3184232_code2420517.pdf?abstractid=3184232&mirid=1 

Martin, E. A., Traugott, M. W., & Kennedy, C. (2005). A review and proposal for a new measure of poll accuracy. Public Opinion Quarterly, 69(3), 342-369. http://www.asasrms.org/Proceedings/y2003/Files/JSM2003-000913.pdf

Price, V., & Neijens, P. (1998). Deliberative polls: Toward improved measures of “informed” public opinion?. International Journal of Public Opinion Research, 10(2), 145-176. https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=3922d1362956bb55df25dbaa8aae8d4706067002 

Let’s see what ChatGPT model 3.5 would generate related to this one.

While mail polling remains a valuable tool for collecting data, advances in technology have led to the development of a variety of non-mail polling methods. In this literature study, we will explore the latest research on non-mail polling methodology.

Firstly, online polling has become increasingly popular, particularly for collecting data quickly and cost-effectively. A study by the Pew Research Center found that online polling can be just as accurate as traditional phone or mail polling, but response rates may be lower, particularly among certain populations such as older adults or those with lower levels of education.

Secondly, phone polling remains a popular method for collecting data, particularly for political polling. However, the rise of mobile phones has presented new challenges for phone polling. A study by the European Social Survey found that mobile phone users are more likely to be younger and have higher levels of education, leading to a potential bias in the results. Additionally, increasing rates of spam and robo-calls may lead to declining response rates.

Thirdly, social media has presented new opportunities for pollsters, particularly for collecting data on younger populations. However, concerns have been raised about the representativeness of social media polls, as they may attract self-selected respondents and may not be representative of the broader population.

Fourthly, researchers have explored the use of text message polling, particularly for collecting data quickly and with high response rates. A study by the National Opinion Research Center (NORC) found that text message polling had higher response rates than email or online polling, particularly among younger populations.

Finally, researchers have also explored the use of location-based polling, which involves collecting data from individuals based on their geographic location. This method can be particularly useful for collecting data on local issues, but concerns have been raised about the potential for privacy violations.

In conclusion, non-mail polling methods have become increasingly popular in recent years, particularly for collecting data quickly and cost-effectively. While online, phone, social media, text message, and location-based polling all have their advantages and disadvantages, researchers have found that no single method is universally superior. The choice of polling method should depend on the research question, the population being surveyed, and the resources available.

Links and thoughts:

Top Tweets of the week:

https://twitter.com/CaseyNewton/status/1646886386031788032

https://twitter.com/robmay/status/1646862194775130114

What’s next for The Lindahl Letter? 

* Week 118: A paper on political debt as a concept vs. technical debt

* Week 119: All that bad data abounds 

* Week 120: That one with an obligatory AI trend’s post

* Week 121: Considering an independent study applied AI syllabus

* Week 122: Will AI be a platform or a service?

If you enjoyed this content, then please take a moment and share it with a friend. If you are new to The Lindahl Letter, then please consider subscribing. New editions arrive every Friday. Thank you and enjoy the year ahead.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.nelsx.com

Searching around on Google Scholar is something that I’m pretty adept at by now. This happens to be the 116th Substack post and almost all of them have involved some type of research. Trying to get a set of the best articles on mail polling methodology was actually really challenging [1]. I know that modern polling has moved away from mail polling in general. It’s expensive. The response rate has gotten worse over time. Probably the worst part about it is that compared to phone or internet based polling it is very slow. My interest here is to really understand polling methodologies. Getting to a high level of understanding about these methodologies will help me evaluate that current literature against automated sentiment analysis. It’s the combination of those two literatures that really has my attention at the moment. 

Google Scholar was actually recommending a related search, “design method mail and internet surveys” [2]. I’ll admit that the results on that search were a little more interesting, but none of it was really targeted at what I wanted to learn about. I ended up broadening my searches to include content related to mail surveys. That yielded a few highly cited sources. One of the problems with this area of research compared to AI or ML is that all the research is not easily accessible for download. 

Brown, M. L. (1965). Use of a postcard query in mail surveys. The Public Opinion Quarterly, 29(4), 635-637.

Sudman, S., Sirken, M. G., & Cowan, C. D. (1988). Sampling rare and elusive populations. Science, 240(4855), 991-996.

Dillman, D. A. (1991). The design and administration of mail surveys. Annual review of sociology, 17(1), 225-249.

Scott, C. (1961). Research on mail surveys. Journal of the Royal Statistical Society: Series A (General), 124(2), 143-195.

Kanuk, L., & Berenson, C. (1975). Mail surveys and response rates: A literature review. Journal of marketing research, 12(4), 440-453.

Maybe you were wondering what ChatGPT model 3.5 would come up with today. Using the prompt, “write a substack post called, ‘A literature study of mail polling methodology’”, a post was created.

A literature study of mail polling methodology

In an era where online and mobile polling have become more popular, it can be easy to overlook the traditional method of mail polling. However, mail polling remains a valuable tool for collecting data, particularly for certain populations. In this literature study, we will explore the latest research on mail polling methodology.

Firstly, studies have shown that mail polling can be particularly effective for reaching older populations, who may be less likely to use online or mobile polling methods. A study by the Pew Research Center found that mail polling had higher response rates among adults aged 65 and older than online or phone polling.

Secondly, mail polling can also be useful for collecting data on sensitive or controversial topics. A study by the National Opinion Research Center (NORC) found that mail polling resulted in higher rates of disclosure on topics such as drug use and sexual behavior, possibly because respondents feel more comfortable disclosing sensitive information in writing rather than in person or over the phone.

Thirdly, mail polling can be useful for collecting data from hard-to-reach populations, such as those without internet or phone access. A study by the American Association for Public Opinion Research (AAPOR) found that mail polling resulted in higher response rates among rural populations than online or phone polling.

Fourthly, researchers have explored the use of incentives to increase response rates in mail polling. Studies have shown that offering incentives such as cash or gift cards can lead to higher response rates, although the effectiveness of incentives may vary depending on the population being surveyed.

Finally, researchers have also explored the use of mixed-mode polling, which combines mail polling with other methods such as online or phone polling. This approach can help reach a wider range of respondents and increase response rates.

In conclusion, mail polling remains a valuable tool for collecting data, particularly for certain populations. While online and mobile polling methods have become more popular, mail polling should not be overlooked, particularly for collecting data on sensitive topics or hard-to-reach populations. The use of incentives and mixed-mode polling can also help increase response rates and improve the accuracy of results.

Links and thoughts:

Top 5 Tweets of the week:

It’s possible that these tweets will not show up as embeds and will just be links. This is due to a change in how Twitter is handling things and not a Substack issue.

https://twitter.com/sama/status/1644878154870427649

https://twitter.com/jdevalk/status/1644439739645194279

https://twitter.com/MKBHD/status/1644562346843467776

https://twitter.com/AndrewYNg/status/1644418518056861696

https://twitter.com/CaseyNewton/status/1644358645084459013 

Footnotes:

[1] https://scholar.google.com/scholar?hl=en&as_sdt=0%2C6&q=mail+polling+methodology&oq=mail+polling+met 

[2] https://scholar.google.com/scholar?hl=en&as_sdt=0,6&qsp=1&q=%22design+method%22+mail+and+internet+surveys&qst=br 

What’s next for The Lindahl Letter? 

* Week 117: A literature study of non-mail polling methodology

* Week 118: A paper on political debt as a concept vs. technical debt

* Week 119: All that bad data abounds 

* Week 120: That one with an obligatory AI trend’s post

* Week 121: Considering an independent study applied AI syllabus

If you enjoyed this content, then please take a moment and share it with a friend. If you are new to The Lindahl Letter, then please consider subscribing. New editions arrive every Friday. Thank you and enjoy the year ahead.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.nelsx.com

Earlier today I did end up getting ChatGPT Plus for a cost of USD $20 a month. That apparently will provide me better availability during high demand, faster response speeds, and priority access to new features [1]. I’m not sure if this subscription will be worth keeping. I’m about to open up the latest model GPT-4 and see what it is able to accomplish in terms of advanced reasoning, complex instructions, and more creativity. I have spent the last 6 weeks thinking about writing these polling related papers. A lot of that time and effort was spent trying to figure out what the trajectory of the current literature was and what that meant for the future of understanding and evaluating sentiment. To me polling is a sampling of sentiment on something. It’s an evaluation of respondent preference or attitude. I’m writing that explanation without using the word opinion. That word choice happened on purpose.

A lot of opportunity exists to study breakdowns in modern polling techniques. This is the start of my series of inquiries into that potential area of study. To be really clear here upfront in this analysis I believe that respondent fatigue, general unavailability, and systemic methodology breakdowns have made modern polling problematic. You can see commentary in very public news sources about people being frustrated with polling [2][3]. I’m surprised so far that more of the literature did not openly discuss the breakdown in previously solid methodologies for polling the public. 

We are here working on these series of literature evaluations, because I’m principally interested in opinion polling and sentiment analysis. You could go out to the Pew Research Center to learn about polling basics [4]. They present research and polling in some pretty easy to understand ways. That visit to Pew might even send you in the direction of the American Association for Public Opinion Research (AAPOR) [5]. The outcome of that digging might point you in the direction of some methods of administering polling. 

* Traditional mail survey questionnaire 

* Phone based delivery of questionnaire

* Email survey questionnaire

* Web based questionnaires

I have spent some time listening to Nate Silver on podcasts over the years. One of the interesting things Nate shared was that a recent batch of polls was more accurate than expected [6]. That made me wonder if the metrology being used had improved or if they were just tuning properly based on some type of modeled expectation. I will caveat here that I read Nate’s book:

Silver, Nate. The signal and the noise: Why so many predictions fail-but some don't. Penguin, 2012.

It was interesting, but I wanted to know more about the future of polling. One of the main questions that I ended up having was about the differences between polling and modeling and what method was better and would end up being more popular over time [7].

* Public attitude extraction

* Indicator based tracking

* Modeled behavior

* Simulated response analysis

* Persona based economic modeling

* Sentiment interviewing

Where did I end up at the end of this analysis? Two things came into focus. First, it was pretty clear to me after digging around that a clear framework for auditing polling methodologies needs to be developed. Second, a sea change in polling is about to occur where modeling as a method or some type of supplemental grounding activity will have to augment traditional polling methodologies. We have already seen extremely convoluted weighting and error ranges become forward reaching into the public mind. 

You could search Google Scholar for online polling best practices [8]. You could also take a look at direct search for “modern polling methodology” and see what shows up [9]. Only one result on the first page of that search had more than 100 citations and that was a handbook. It came in at 172 citations. 

Donsbach, W., & Traugott, M. W. (Eds.). (2007). The SAGE handbook of public opinion research. Sage.

The PDF was not available over at ResearchGate or on Google Scholar. You can buy the hardcover from Sage for $215 dollars which seems a little bit out of hand. You can rent or buy the eBook from Sage as well which for a lifetime copy would set you back $117 [10].

I did prompt ChatGPT from OpenAI using the GPT-4 model to generate a paper called, "A literature review of modern polling methodology" that turned out to be interesting. My exact prompt on this one was, “write an academic paper called, ‘A literature review of modern polling methodology’”.

Oddly enough on the first attempt it produced a ton of content then had a “network error” with a more specific message of, “There was an error generating a response.” My only option to move forward was to click the “Regenerate response” box and hope for the best. It took 4 regeneration attempts to get a complete output. 

Title: A Literature Review of Modern Polling Methodology

Abstract

The present study aims to provide a comprehensive review of the modern polling methodologies, analyzing their strengths and weaknesses, as well as the ongoing challenges faced by the polling industry. This literature review discusses traditional and emerging methodologies, such as random-digit dialing, online surveys, and mixed-mode approaches. Moreover, the impact of social media on public opinion polling is considered, and the potential of data mining and machine learning for future advancements in the field is explored.

Introduction

Public opinion polling plays a significant role in modern democracies, shaping political strategies, and informing policy-making processes. Over the years, several polling methodologies have been developed and refined to collect accurate and reliable data on public opinion. However, recent events, such as the 2016 United States Presidential Election and the Brexit referendum, have brought the accuracy and reliability of polling methods into question. This literature review aims to examine the current state of polling methodologies, evaluate their strengths and weaknesses, and discuss the future directions of public opinion polling.

Traditional Polling Methodologies

1.1. Random-Digit Dialing (RDD)

RDD has been the gold standard of telephone survey sampling for decades. By generating random phone numbers, researchers ensure that each household has an equal chance of being included in the survey. However, the rapid decline in landline use and the increasing preference for mobile phones has challenged RDD's efficacy (Pew Research Center, 2019).

1.2. Area Probability Sampling

Area probability sampling involves selecting a sample of respondents from a predefined geographical area. This method offers an alternative to RDD and has been proven useful for face-to-face surveys (Lynn & Jäckle, 2020). However, it can be expensive and time-consuming compared to other sampling techniques.

Online Polling Methodologies

2.1. Online Panels

Online panels consist of pre-recruited participants who have agreed to take part in surveys. These panels provide a cost-effective and faster alternative to traditional methodologies. Nevertheless, concerns about sample representativeness and potential biases remain (Baker et al., 2013).

2.2. River Sampling

River sampling is an online methodology where respondents are recruited as they visit websites, often through ads or pop-ups. This method can provide a large number of respondents quickly. However, the lack of control over the selection process raises concerns about the quality and representativeness of the sample (Mercer, 2018).

Mixed-Mode Approaches

Mixed-mode approaches combine multiple data collection methods, such as telephone and online surveys, to compensate for the shortcomings of individual methods (Vavreck & Rivers, 2008). This approach has gained popularity as a means to improve representativeness and reduce nonresponse bias. However, challenges related to mode effects and data integration persist (De Leeuw, 2021).

The Impact of Social Media on Public Opinion Polling

Social media platforms have transformed how people communicate and consume information. As such, there is growing interest in harnessing social media data to understand public opinion (Jungherr et al., 2021). Sentiment analysis and network analysis have emerged as promising techniques for analyzing social media data, but concerns about data quality, privacy, and representativeness need to be addressed (Stier et al., 2020).

The Future of Polling: Data Mining and Machine Learning

Data mining and machine learning techniques offer potential for improving the accuracy and efficiency of public opinion polling. For instance, these techniques can be employed to correct biases, enhance sample representativeness, and identify patterns in survey responses (Wang et al., 2019). However, the ethical implications of these methods, particularly with

You may have noticed that the model output stopped in the middle of a sentence. It seemed like a better idea to change up the prompt for GPT-4 and request it to outline a paper instead of writing it. That seemed like a better way to get an actual complete set of output from the model. The previous 4 network errors were actually rather frustrating. OpenAI is only allowing 30 prompts per 3 hours and having to use them up to overcome network errors was frustrating. 

Title: A Literature Review of Modern Polling Methodology

Abstract:

This paper provides a comprehensive review of the modern polling methodology, focusing on the evolution of survey techniques, data collection methods, and analysis tools in the field of public opinion research. By examining the strengths and weaknesses of these methodologies, we aim to identify best practices and guide future research in the field of political and social polling.

Introduction

1.1 Background and purpose of the study

1.2 Scope and limitations of the review

Evolution of Polling Methodology

2.1 Early beginnings: Straw polls and face-to-face interviews

2.2 Telephone surveys: The rise and decline

2.3 The advent of the internet: Online surveys and panels

2.4 Mobile-based polling: SMS and mobile app surveys

2.5 Social media as a data source

Data Collection Techniques

3.1 Probability sampling methods

3.1.1 Simple random sampling

3.1.2 Systematic sampling

3.1.3 Stratified sampling

3.1.4 Cluster sampling

3.2 Non-probability sampling methods

3.2.1 Convenience sampling

3.2.2 Quota sampling

3.2.3 Snowball sampling

3.2.4 Purposive sampling

3.3 Comparing probability and non-probability sampling techniques

Questionnaire Design and Implementation

4.1 Principles of effective questionnaire design

4.2 Types of survey questions

4.2.1 Open-ended questions

4.2.2 Closed

Links and thoughts:

Top 5 Tweets of the week:

 

Footnotes:

[1]

https://chat.openai.com/chat

 

[2] https://www.nytimes.com/interactive/2022/10/24/opinion/frustrated-with-polling-pollsters-are-too.html 

[3] https://www.nationalaffairs.com/publications/detail/the-trouble-with-polling 

[4] https://www.pewresearch.org/course/public-opinion-polling-basics/ 

[5]

https://aapor.org/

 

[6] https://fivethirtyeight.com/videos/polls-havent-been-this-accurate-since-at-least-1998/

[7] https://www.majoritystrategies.com/blog/polling-or-modeling-which-do-you-need/

[8] https://scholar.google.com/scholar?hl=en&as_sdt=0%2C10&q=best+practices+online+polling&oq=online+polling 

[9] https://scholar.google.com/scholar?hl=en&as_sdt=0%2C10&q=modern+polling+methodology&btnG= 

[10] https://us.sagepub.com/en-us/nam/the-sage-handbook-of-public-opinion-research/book228115 

What’s next for The Lindahl Letter? 

* Week 116: A literature study of mail polling methodology

* Week 117: A literature study of non-mail polling methodology

* Week 118: A paper on political debt as a concept vs. technical debt

* Week 119: All that bad data abounds 

* Week 120: That one with an obligatory AI trend’s post

If you enjoyed this content, then please take a moment and share it with a friend. If you are new to The Lindahl Letter, then please consider subscribing. New editions arrive every Friday. Thank you and enjoy the year ahead.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.nelsx.com

Imagine you move part of your workload to an environment that you don’t fully own. That used to be a datacenter and more recently it is probably a cloud environment. Sooner or later you might think about how to secure that environment in terms of hardware-based security or other ways to secure things. Most of the promotional pages on the internet covering this one try to bring forward the idea of securing code and data [1]. Seriously, the idea of confidential computing is everywhere on these cloud pages, but not something you hear about all the time generally [2][3][4]. It is a topic that receives a lot of industry specific coverage related to managing and operating cloud environments. 

The low number of highly cited “confidential computing” articles over at Google Scholar was probably indicative of the relative interest in this topic [5]. Very few of the available academic works are highly cited in this area. It’s actually an area where some research opportunity exists related to a survey of security and the outcomes of confidential computing in practice. 

A few of the more interesting ones with a higher level of citation ended up being:

Mulligan, D. P., Petri, G., Spinale, N., Stockwell, G., & Vincent, H. J. (2021, September). Confidential Computing—a brave new world. In 2021 international symposium on secure and private execution environment design (SEED) (pp. 132-138). IEEE. https://dominicpm.github.io/publications/mulligan-seed2021.pdf

Rashid, F. Y. (2020). The rise of confidential computing: Big tech companies are adopting a new security model to protect data while it's in use-[news]. IEEE Spectrum, 57(6), 8-9. https://ieeexplore.ieee.org/iel7/6/9099910/09099920.pdf

Zhu, J., Hou, R., Wang, X., Wang, W., Cao, J., Zhao, B., ... & Meng, D. (2020, May). Enabling rack-scale confidential computing using heterogeneous trusted execution environment. In 2020 IEEE Symposium on Security and Privacy (SP) (pp. 1450-1465). IEEE. https://heartever.github.io/files/hetee.pdf

The central question here seems to be if you are going to have your data and run your workloads in the cloud how do you really make sure that effort is confidential. At this point in my analysis, I thought it might be interesting to see what ChatGPT would produce on this topic. 

OpenAI ChatGPT Prompt: “scrap that and rewrite it with ethics included”

Sure, here's a rewritten version of the substack post about AI and confidential computing with a focus on ethics:

The intersection of AI and confidential computing has become increasingly important as we realize the importance of privacy and security in computing. Confidential computing is a field that seeks to protect sensitive data and computations by ensuring that they remain encrypted and secure throughout the computing process. Meanwhile, AI relies heavily on large amounts of data to make accurate predictions and decisions, but this data is often sensitive and needs to be kept confidential to protect individuals’ privacy. This is where confidential computing can play an important role, as it can ensure that sensitive information remains private, even when being processed by AI algorithms.

The integration of confidential computing into AI has several benefits. First, it ensures that personal data is kept secure and private, which is crucial for industries such as healthcare and finance. Second, it enables collaboration between organizations without risking the leak of sensitive information. Lastly, it can improve the accuracy and effectiveness of AI models as more data can be used for training without compromising privacy.

However, there are also ethical considerations when it comes to the intersection of AI and confidential computing. For example, there is a risk that confidential computing could be used to conceal unethical or discriminatory practices. It is important to consider how confidential computing is used and to ensure that it is not used to violate ethical principles. Additionally, there is a need to ensure that confidential computing is not used to perpetuate biases that already exist in datasets.

To address these ethical concerns, it is important to ensure that the development and deployment of confidential computing technologies are guided by ethical principles. Transparency and accountability should be central to the development of these technologies, and there should be a focus on ensuring that they are used in a way that promotes fairness, accountability, and transparency. This requires collaboration between computer scientists, ethicists, and policymakers to ensure that these principles are integrated into the design and use of confidential computing technologies.

In conclusion, the intersection of AI and confidential computing has promising implications for privacy and security. However, it is important to ensure that these technologies are developed and used ethically. By integrating ethical considerations into the design and use of confidential computing technologies, we can ensure that these technologies are used in a way that promotes fairness, accountability, and transparency.

Alright, so you can get a sense of what I produced related to confidential computing, then you can get a sense of what the ChatGPT model produced and it’s interesting. It’s an interesting thing here. I spent a couple hours researching and doing work on what exactly people are doing with confidential computing trying to figure out what information was available from scholarly sources on how people were doing confidential computing and how that methodology was occurring and then wrote a Substack post. It took ChatGPT a few seconds to spit out what it produced. I think the depth of the reference to specific sources I think the difference in looking at what happens from the scholarly output compared to how it’s being used, none of that occurred within the ChatGPT. It definitely is very surface level in terms of how it made the argument, but it did produce it very quickly.

Links and thoughts:

Top 7 Tweets of the week:

Footnotes:

[1] https://www.intel.com/content/www/us/en/security/confidential-computing.html 

[2] https://azure.microsoft.com/en-us/solutions/confidential-compute/

[3] https://cloud.google.com/confidential-computing

[4] https://www.ibm.com/topics/confidential-computing 

[5] https://scholar.google.com/scholar?hl=en&as_sdt=0%2C5&q=confidential+computing&btnG= 

What’s next for The Lindahl Letter? 

* Week 115: A literature review of modern polling methodology

* Week 116: A literature study of mail polling methodology

* Week 117: A literature study of non-mail polling methodology

* Week 118: A paper on political debt as a concept vs. technical debt

* Week 119: All that bad data abounds 

If you enjoyed this content, then please take a moment and share it with a friend. If you are new to The Lindahl Letter, then please consider subscribing. New editions arrive every Friday. Thank you and enjoy the year ahead.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.nelsx.com

You may remember that I listened to an audiobook during a road trip back to Kansas about AI. 

Kissinger, H. A., Schmidt, E., & Huttenlocher, D. (2021). The age of AI: and our human future. Hachette UK.  

Former CEO of Google Eric Schmidt has had a lot to say about the future of AI and a lot of that has been grounded in the implications of AI on society. It’s important to set the foundation of any introduction to AI ethics on the implications to people and society. 

Crowdsourcing a really solid introduction to AI ethics seems like something that would be easy enough to achieve. People have a lot of somewhat divergent thoughts on what exactly AI ethics includes. This effort is my attempt at structuring an introduction to AI ethics. I’ll take this and produce an independent study version of this using Overleaf LaTex to make it extra awesome. My last run at this was about 6 months ago during week 86 that was primarily about ML ethics centering on fairness, bias, and privacy as core topics [1]. It might be a good start to dig deeper this time around and look for more topics to include with a larger focus on AI and not staying limited to the world of ML. I cloned my previous project in Overleaf and then removed all the extra content. Not only should it be pretty easy to take this structure or outline and expand it to a longer form for publication, but also it is probably time to revisit using LaTeX before that rather academic skill set fades.

What are other major topics to consider besides fairness, bias, and privacy?

* Laws and legislation

* Intellectual property 

* Academic citation

* Human-centered design

* Examples (applied or theoretical)

* Data sourcing

* Labor practices

* Frameworks

* Operationalizing

* Misinformation

You could go out and read “The Ethics of Artificial Intelligence” by Nick Bostrom and Eliezer Yudkowsky [2]. Or maybe go out to the “Everyday Ethics for Artificial Intelligence” from the team over at IBM [3].

As a little bonus for you here, instead of closing out this Substack post I’m going to provide you with a few chapters from a session of content generation I had with OpenAI’s ChatGPT. The session was seeded with a request to write an introduction to AI ethics. You will find that my prompts are very direct and highly word economic. The output here is really just based on getting the ChatGPT large language model to keep generating as the session output is limited per interaction. You will see evidence of this as it sometimes just sometimes appears to stop mid chapter or closes out abruptly.

OpenAI ChatGPT Prompt: “write a summary for the book”

The book is about the ethical considerations of artificial intelligence (AI) and its impact on society. It covers a wide range of topics including bias and fairness, transparency and explainability, privacy and security, the impact of AI on employment and the economy, the use of AI in sensitive domains, and the future of AI and its potential impact on society. The book emphasizes that ethical considerations surrounding AI are complex and multifaceted, and that it is crucial to stay informed about the latest developments in the field. It also highlights the importance of developing strategies to ensure that the benefits of AI are shared by all members of society, including policies such as retraining programs, universal basic income, and government oversight. The book also emphasizes that AI ethics is an interdisciplinary field that brings together experts from various domains such as computer science, philosophy, law, sociology, psychology, and policy.

OpenAI ChatGPT Prompt: “why should i read this book”

You should read this book because it provides a comprehensive overview of the ethical considerations surrounding AI and its impact on society. The book covers a wide range of topics that are important for understanding the current and future implications of AI on society. It highlights the potential benefits and risks of AI and provides strategies for addressing these challenges. Additionally, the book emphasizes the importance of staying informed about the latest developments in AI and the importance of developing policies to ensure that the benefits of AI are shared by all members of society.

As AI is a rapidly advancing technology that has the potential to shape the future of humanity in ways that are difficult to predict, it is important to be aware of the ethical considerations surrounding AI. This book is a valuable resource for anyone who wants to understand the impact of AI on society and the ethical considerations that need to be taken into account as the technology continues to advance.

OpenAI ChatGPT Prompt: “what would you title book”

"AI Ethics: Navigating the Challenges and Opportunities of Artificial Intelligence"

OpenAI ChatGPT Prompt: “tell me the chapters again”

The book has the following chapters:

Chapter 1: Introduction to AI Ethics

Chapter 2: Bias and Fairness in AI

Chapter 3: Transparency and Explainability in AI

Chapter 4: Privacy and Security in AI

Chapter 5: The Impact of AI on Employment and the Economy

Chapter 6: The Use of AI in Sensitive Domains

Chapter 7: The Future of AI and its Potential Impact on Society

Chapter 8: Conclusion

Chapter 9: References

OpenAI ChatGPT Prompt: “write a dedication for the book”

"Dedicated to all those who strive to make AI a force for good, and to the future generations who will be impacted by its development."

OpenAI ChatGPT Prompt: “who is the author”

As an AI, I do not have a physical presence, so I cannot be an author of a book. But I can provide you with the information and the content of the book.

OpenAI ChatGPT Prompt: “ok. write the first chapter”

Chapter 1: Introduction to AI Ethics

Artificial intelligence (AI) is rapidly advancing and has the potential to transform society in countless ways. As AI becomes more prevalent in our lives, it is crucial to consider the ethical implications of its development and use. AI ethics is the study of the ethical considerations surrounding the design, development, deployment, and use of AI systems.

This chapter will introduce the key ethical issues associated with AI and provide an overview of the field of AI ethics. We will begin by defining AI and discussing its various forms, including narrow AI and general AI. We will then explore the potential benefits and risks of AI, highlighting the ways in which it can be used to improve people's lives and the potential for AI to cause harm.

Next, we will discuss the importance of considering ethical considerations in the development and use of AI. We will explore the role of stakeholders in AI, including developers, users, and society as a whole, and the responsibilities of each of these groups in ensuring that AI is developed and used ethically.

Finally, we will introduce the main ethical frameworks used in AI ethics, including consequentialism, deontology, and virtue ethics. We will also discuss the concept of "machine ethics" and the potential for AI systems to have their own moral principles.

The goal of this chapter is to provide a foundation for the ethical considerations surrounding AI and set the stage for the rest of the book. As we explore the various ethical issues in more depth in the chapters to come, it is important to keep in mind that the ethical considerations surrounding AI are complex and multifaceted. The field of AI ethics is constantly evolving, and it is important to approach these issues with an open mind and a willingness to consider multiple perspectives.

OpenAI ChatGPT Prompt: “ok. write the second chapter”

Chapter 2: Bias and Fairness in AI

One of the most important ethical considerations surrounding AI is the potential for AI systems to perpetuate or exacerbate societal biases. Bias in AI can occur at various stages of the AI development process, including in the data used to train models, in the algorithms used to develop models, and in the deployment of models in real-world settings.

This chapter will explore the concept of bias in AI and discuss strategies for addressing bias in AI systems. We will begin by defining bias and discussing the different types of bias that can occur in AI systems. We will then explore the ways in which bias can occur in the data used to train models, including issues such as underrepresentation and overrepresentation of certain groups.

Next, we will discuss the ways in which bias can be introduced in the algorithms used to develop models, including issues such as fairness and discrimination. We will also explore the potential for AI to perpetuate or exacerbate societal biases, such as discrimination against marginalized groups.

To mitigate these issues, we will discuss different strategies for addressing bias in AI systems. These include techniques for detecting and correcting bias in data and algorithms, as well as the use of fairness metrics to evaluate the performance of AI systems. We will also discuss the importance of transparency and explainability in AI, which can help to ensure that AI systems are fair and unbiased.

Finally, we will discuss the role of regulation and policy in addressing bias in AI, including the importance of government oversight and the need for industry-wide standards and guidelines.

It's important to note that addressing bias in AI is an ongoing process that requires constant monitoring and improvement. It requires a combination of technical, legal and ethical efforts to make sure that AI systems are fair and unbiased towards all individuals and groups.

OpenAI ChatGPT Prompt: “ok. write chapter three”

Chapter 3: Transparency and Explainability in AI

As AI systems become increasingly prevalent in society, it is important to ensure that they are transparent and explainable to humans. Transparency refers to the ability to understand how an AI system makes decisions, and explainability refers to the ability to understand the reasoning behind those decisions.

This chapter will explore the challenges of transparency and explainability in AI and discuss strategies for addressing these challenges. We will begin by defining transparency and explainability in AI and discussing the importance of these concepts in ensuring that AI systems are trustworthy and accountable.

Next, we will discuss the challenges of achieving transparency and explainability in AI, including issues such as the complexity of AI systems, the use of "black box" models, and the limitations of current explainability techniques. We will also explore the potential for AI to make decisions that are difficult or impossible for humans to understand or explain.

To mitigate these challenges, we will discuss different strategies for achieving transparency and explainability in AI. These include techniques for making AI systems more interpretable, such as the use of decision trees and rule-based models, and the use of explainability methods such as feature attribution and saliency maps. We will also discuss the importance of human-centered design in AI, which can help to ensure that AI systems are understandable and usable by humans.

Finally, we will discuss the role of regulation and policy in promoting transparency and explainability in AI, including the importance of government oversight and the need for industry-wide standards and guidelines.

It's important to note that transparency and explainability are important not only for ensuring the accountability of AI systems, but also for building trust with the public. As AI systems are increasingly integrated into society, it becomes essential to develop methods to ensure that AI systems are understandable and explainable to the people who will be impacted by them.

OpenAI ChatGPT Prompt: “ok. write chapter four”

Chapter 4: Privacy and Security in AI

As AI systems become more prevalent in society, it is crucial to consider the privacy and security implications of their development and use. Privacy refers to the ability to control the collection, use, and dissemination of personal data, while security refers to the protection of personal data and AI systems from unauthorized access and malicious attacks.

This chapter will explore the privacy and security challenges associated with AI and discuss strategies for addressing these challenges. We will begin by defining privacy and security in the context of AI and discussing the importance of these concepts in ensuring that AI systems are trustworthy and secure.

Next, we will discuss the privacy and security challenges associated with AI, including issues such as data breaches, data misuse, and the potential for AI-enabled surveillance. We will also explore the potential for AI systems to be used for malicious purposes, such as cyber attacks and identity theft.

To mitigate these challenges, we will discuss different strategies for ensuring privacy and security in AI. These include techniques for protecting personal data, such as encryption and anonymization, and the use of security measures to protect AI systems from unauthorized access and malicious attacks. We will also discuss the importance of responsible data management practices, such as data minimization and data governance, which can help to ensure that personal data is handled in a secure and ethical manner.

Finally, we will discuss the role of regulation and policy in promoting privacy and security in AI, including the importance of government oversight and the need for industry-wide standards and guidelines.

It's important to note that privacy and security are essential to the responsible development and use of AI. As AI systems are increasingly integrated into society, it becomes essential to develop methods to ensure that personal data is protected and AI systems are secure from malicious attacks.

OpenAI ChatGPT Prompt: “ok. write chapter five”

Chapter 5: The Impact of AI on Employment and the Economy

As AI continues to advance, it has the potential to transform the way we work and the structure of the economy. While AI has the potential to create new jobs and improve productivity, it also has the potential to displace existing jobs and contribute to income inequality.

This chapter will explore the impact of AI on employment and the economy and discuss strategies for addressing these challenges. We will begin by discussing the potential benefits and risks of AI in the workplace, including the potential for AI to improve productivity and create new jobs, and the potential for AI to displace existing jobs and contribute to income inequality.

Next, we will discuss the potential impact of AI on different sectors of the economy, including manufacturing, healthcare, and finance. We will also explore the potential for AI to change the way we work, including the rise of the gig economy and the potential for remote work to become more prevalent.

To mitigate these challenges, we will discuss different strategies for addressing the impact of AI on employment and the economy. These include policies such as retraining programs and universal basic income, as well as the importance of creating an economic and social safety net for those who may be displaced by AI. We will also discuss the importance of investing in education and training to ensure that workers have the skills needed to succeed in the new economy.

Finally, we will discuss the role of regulation and policy in addressing the impact of AI on employment and the economy, including the importance of government oversight and the need for industry-wide standards and guidelines.

It's important to note that the impact of AI on employment and the economy is a complex issue that requires a multifaceted approach. As AI continues to advance, it is crucial to consider the potential impact on workers and the economy and to develop strategies to ensure that the benefits of AI are shared by all members of society.

OpenAI ChatGPT Prompt: “ok. write chapter six”

Chapter 6: The Use of AI in Sensitive Domains

As AI systems become more advanced and prevalent in society, they are increasingly being used in sensitive domains such as healthcare, criminal justice, and military applications. The use of AI in these domains raises important ethical considerations, including issues of accountability, fairness, and transparency.

This chapter will explore the ethical considerations associated with the use of AI in sensitive domains. We will begin by discussing the different types of sensitive domains in which AI is being used, including healthcare, criminal justice, and military applications. We will then explore the potential benefits and risks of AI in these domains, highlighting the ways in which AI can be used to improve outcomes and the potential for AI to cause harm.

Next, we will discuss the ethical considerations associated with the use of AI in sensitive domains, including issues of accountability, fairness, and transparency. We will also explore the potential for AI to perpetuate or exacerbate societal biases, such as discrimination against marginalized groups.

To mitigate these issues, we will discuss different strategies for addressing the ethical considerations associated with the use of AI in sensitive domains. These include techniques for detecting and correcting bias in data and algorithms, as well as the use of fairness metrics to evaluate the performance of AI systems. We will also discuss the importance of transparency and explainability in AI, which can help to ensure that AI systems are fair and unbiased.

Finally, we will discuss the role of regulation and policy in addressing the ethical considerations associated with the use of AI in sensitive domains, including the importance of government oversight and the need for industry-wide standards and guidelines.

It's important to note that the use of AI in sensitive domains is a complex and nuanced issue that requires a thorough understanding of the ethical considerations involved. As AI systems are increasingly used in these domains, it is crucial to consider the potential impact on society and to develop strategies to ensure that the use of AI is safe, fair, and transparent.

OpenAI ChatGPT Prompt: “ok. write chapter seven”

Chapter 7: The Future of AI and its Potential Impact on Society

As AI continues to advance, it has the potential to shape the future of humanity in ways that are difficult to predict. While AI has the potential to bring about significant benefits, such as improved healthcare and increased productivity, it also has the potential to cause harm, such as job displacement and the erosion of privacy.

This chapter will explore the potential impact of AI on society in the future and discuss strategies for addressing these challenges. We will begin by discussing the potential benefits and risks of AI in the future, including the potential for AI to improve our lives and the potential for AI to cause harm.

Next, we will discuss the concept of "superintelligent AI" and the potential impact of AI on society if machines surpass human intelligence. We will also explore the potential impact of AI on issues such as privacy, security, and democracy.

To mitigate these challenges, we will discuss different strategies for addressing the future impact of AI on society. These include policies such as retraining programs and universal basic income, as well as the importance of creating an economic and social safety net for those who may be displaced by AI. We will also discuss the importance of investing in education and training to ensure that workers have the skills needed to succeed in the new economy.

Finally, we will discuss the role of regulation and policy in addressing the future impact of AI on society, including the importance of government oversight and the need for industry-wide standards and guidelines.

It's important to note that the future of AI is uncertain and that it is difficult to predict the long-term impact of AI on society. However, it is crucial to consider the potential impact of AI on society and to develop strategies to ensure that the benefits of AI are shared by all members of society. This includes both short-term and long-term considerations, as well as the development of regulation and policy that can guide the responsible development of AI for the future.

OpenAI ChatGPT Prompt: “ok. write chapter eight”

Chapter 8: Conclusion

Artificial intelligence (AI) is a rapidly advancing technology with the potential to transform society in countless ways. The ethical considerations surrounding AI are complex and multifaceted, and it is important to approach these issues with an open mind and a willingness to consider multiple perspectives.

This book has covered various ethical issues associated with AI, including bias and fairness, transparency and explainability, privacy and security, the impact of AI on employment and the economy, the use of AI in sensitive domains, and the future of AI and its potential impact on society.

In conclusion, it is important to keep in mind that the ethical considerations surrounding AI are constantly evolving, and it is crucial to stay informed about the latest developments in the field. It is also important to consider the potential impact of AI on society and to develop strategies to ensure that the benefits of AI are shared by all members of society. This includes policies such as retraining programs, universal basic income, and government oversight. Additionally, it is important to invest in education and training to ensure that workers have the skills needed to succeed in the new economy.

AI ethics is an interdisciplinary field that brings together experts from various domains such as computer science, philosophy, law, sociology, psychology, and policy. As AI continues to advance, it is crucial to continue the conversation about the ethical considerations surrounding AI and to work together to ensure that AI is developed and used in a responsible and ethical manner.

OpenAI ChatGPT Prompt: “ok. write a references section”

References:

Bostrom, N. (2014). Superintelligence: Paths, Dangers, and Strategies. Oxford University Press.

Domingos, P. (2015). The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World. Basic Books.

Floridi, L. (2019). The Ethics of Artificial Intelligence. Oxford University Press.

Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Adaptive Computation and Machine Learning series). MIT Press.

Gudivada, V. N., Raghavan, V. V., & Riedl, J. (Eds.). (2019). Artificial Intelligence Ethics: A Primer. Springer.

Kember, S., & Loke, L. (2019). Artificial Intelligence: A Guide for Thinking Humans. Farrar, Straus and Giroux.

Russell, S. J., & Norvig, P. (2016). Artificial Intelligence: A Modern Approach (3rd ed.). Prentice Hall.

Zeng, X., & Liu, Y. (Eds.). (2018). Handbook of Research on Artificial Intelligence Ethics and Society. IGI Global.

Note: These are a sample of books and references about AI ethics, there are more recent and thorough resources available.

Footnotes:

[1]

[2] https://intelligence.org/files/EthicsofAI.pdf 

[3] https://www.ibm.com/watson/assets/duo/pdf/everydayethics.pdf 

What’s next for The Lindahl Letter? 

* Week 114: How does confidential computing work?

* Week 115: A literature review of modern polling methodology

* Week 116: A literature study of mail polling methodology

* Week 117: A literature study of non-mail polling methodology

* Week 118: A paper on political debt as a concept vs. technical debt

If you enjoyed this content, then please take a moment and share it with a friend. If you are new to The Lindahl Letter, then please consider subscribing. New editions arrive every Friday. Thank you and enjoy the year ahead.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.nelsx.com

Lectures related to this topic are mostly about convolutional neural networks and visual recognition systems. My searches were explicitly for autonomous vehicles and did not directly include any of the methods being deployed. That in part was due to my interest in going into higher levels of analysis this time around. My searches of Google Scholar on this topic of autonomous vehicles returned results with a lot fewer citations than I was expecting to find [1]. Three of the papers in the first 30 results had more than 1,000 citations.

Fagnant, D. J., & Kockelman, K. (2015). Preparing a nation for autonomous vehicles: opportunities, barriers and policy recommendations. Transportation Research Part A: Policy and Practice, 77, 167-181. https://www.caee.utexas.edu/prof/kockelman/public_html/TRB14EnoAVs.pdf 

Shah, S., Dey, D., Lovett, C., & Kapoor, A. (2018). Airsim: High-fidelity visual and physical simulation for autonomous vehicles. In Field and Service Robotics: Results of the 11th International Conference (pp. 621-635). Springer International Publishing. https://arxiv.org/pdf/1705.05065.pdf 

Bonnefon, J. F., Shariff, A., & Rahwan, I. (2016). The social dilemma of autonomous vehicles. Science, 352(6293), 1573-1576. https://arxiv.org/pdf/1510.03346 

The rest of the scholarly articles seemed to have around a couple hundred citations. Maybe the collection of scholars interested in autonomous vehicle research is about that size. In practical terms it is probably a fairly expensive area of study. Even building simulated models would be computationally expensive. Collecting real world model data would be cost prohibitive for most researchers. 

Faisal, A., Kamruzzaman, M., Yigitcanlar, T., & Currie, G. (2019). Understanding autonomous vehicles. Journal of transport and land use, 12(1), 45-72. https://conservancy.umn.edu/bitstream/handle/11299/209218/JTLU_vol-12_pp45-72.pdf?sequence=1

Schwarting, W., Alonso-Mora, J., & Rus, D. (2018). Planning and decision-making for autonomous vehicles. Annual Review of Control, Robotics, and Autonomous Systems, 1, 187-210. http://alonsomora.com/docs/18-schwarting-AR.pdf

Kato, S., Takeuchi, E., Ishiguro, Y., Ninomiya, Y., Takeda, K., & Hamada, T. (2015). An open approach to autonomous vehicles. IEEE Micro, 35(6), 60-68. http://cs.furman.edu/~tallen/csc271/source/openAppr.pdf

You will notice pretty quickly that all of those scholarly works are aging a bit compared to where we are now at the doorstep of modernity. I’ll be curious about digging into things a bit more over time to find more current state reviews of autonomous vehicles.

Links and thoughts:

Top 5 Tweets of the week:

Footnotes:

[1] https://scholar.google.com/scholar?hl=en&as_sdt=0%2C6&q=autonomous+vehicles&btnG=&oq=autonomous+v  

What’s next for The Lindahl Letter? 

* Week 113: Structuring an introduction to AI ethics

* Week 114: How does confidential computing work?

* Week 115: A literature review of modern polling methodology

* Week 116: A literature study of mail polling methodology

* Week 117: A literature study of non-mail polling methodology

If you enjoyed this content, then please take a moment and share it with a friend. If you are new to The Lindahl Letter, then please consider subscribing. New editions arrive every Friday. Thank you and enjoy the year ahead.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.nelsx.com

We have reached the 7th installment of the new series for 2023 related to AI. In just a couple of weeks we are going to venture out of these framing topics into the heart of my journey back into polling and sentiment analysis. Toward the end of that journey it will be very clear on the relationships between AGI, AI, and sentiment analysis. Processing to the point of understanding then adding a degree of directionality in terms of sentiment may be beyond the current state of things at this moment. A lot of debate will go into what is understanding, the occurrence of it, and does it have to be sustained to be relevant. Commonly people try to sum that debate up within the context of next best alternative consideration and that is interesting. However, that debate could be summed up within the analogy of trying to argue that a really well drawn map could provide understanding. It certainly could provide the pathing and the next best routing assuming you have a general idea of where you are going and that path is covered on the map. 

Let’s zoom back out for a minute and look at a relatively current webinar. A recent one hour webinar from Stanford online professor Christopher Potts related to GTP-3 & Beyond was pretty interesting. It’s easy to find on YouTube and you can watch it faster than 1x if you enjoy that sort of thing.

Outside of that consideration, I’m wondering if we are going to end up moving from people writing books and articles to a world where people are certifying books and articles for correctness. Some sort of model is used to produce content and then a person edits it to or just verifies its correctness. People have spent a lot of time trying to figure out how to handle natural language processing (NLP). As editors of that content people could act as the ultimate gatekeeper of knowledge and correctness within what is spit out of the systems. We are after all capable of processing natural language ourselves. It’s just a lot harder to explain or rationalize the rule systems that each individual person uses to achieve that objective.

Here are 5 scholarly works related to NLP:

Manning, C., & Schutze, H. (1999). Foundations of statistical natural language processing. MIT press. http://www.cs.cornell.edu/home/llee/papers/topost.pdf

Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with Python: analyzing text with the natural language toolkit. " O'Reilly Media, Inc.".

Chowdhary, K., & Chowdhary, K. R. (2020). Natural language processing. Fundamentals of artificial intelligence, 603-649. https://strathprints.strath.ac.uk/2611/1/strathprints002611.pdf

Hirschberg, J., & Manning, C. D. (2015). Advances in natural language processing. Science, 349(6245), 261-266. https://nlp.stanford.edu/~manning/xyzzy/Hirschberg-Manning-Science-2015.pdf 

Manning, C. D., Surdeanu, M., Bauer, J., Finkel, J. R., Bethard, S., & McClosky, D. (2014, June). The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations (pp. 55-60). https://aclanthology.org/P14-5010.pdf 

You could go out and watch Christopher Manning’s “Natural language processing with deep learning CS224N/Ling284” 23 video course on YouTube [1]. This one contains a lot of content. 

Maybe you were looking for a more media rich introduction to NLP. The team over at TensorFlow also has a collection of 6 videos on the topic that are going to be a lot more visually involved [2]. They are also considerably shorter than the 23 video course from Christopher Manning. 

Rounding this one out will be a video from the IBM Cloud team which was pretty decent. 

Links and thoughts:

Top 4 Tweets of the week:

Footnotes:

[1]

[2]

What’s next for The Lindahl Letter? 

* Week 112: Autonomous vehicles

* Week 113: Structuring an introduction to AI ethics

* Week 114: How does confidential computing work?

* Week 115: A literature review of modern polling methodology

* Week 116: A literature study of mail polling methodology

If you enjoyed this content, then please take a moment and share it with a friend. If you are new to The Lindahl Letter, then please consider subscribing. New editions arrive every Friday. Thank you and enjoy the year ahead.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.nelsx.com

In total the largest knowledge graph ever created on the shoulders of giants happens to be the college academy of knowledge compiled as a part of our higher education traditions. That knowledge graph is inherently built on connections and the learning patterns of academics. It would have to be considered to be a very human based aggregate not a computer based one. It’s possible that could change over time, but I’m not entirely convinced that is going to happen in the short term. The totality of academics is a much more complex knowledge collection than any model. It also contains a lot of conflicting arguments and disagreement. 

Here is a video from IBM Technology that explains, “What is a knowledge graph?”

If you wanted to really go deeper, then you could check out this video from Yanic.

Wang, C., Liu, X., & Song, D. (2020). Language models are open knowledge graphs. arXiv preprint arXiv:2010.11967. https://arxiv.org/pdf/2010.11967.pdf 

Here are 3 academic papers that are highly cited within the context of knowledge graphs.

Nickel, M., Murphy, K., Tresp, V., & Gabrilovich, E. (2015). A review of relational machine learning for knowledge graphs. Proceedings of the IEEE, 104(1), 11-33. https://ieeexplore.ieee.org/ielaam/5/7360840/7358050-aam.pdf 

Ji, S., Pan, S., Cambria, E., Marttinen, P., & Philip, S. Y. (2021). A survey on knowledge graphs: Representation, acquisition, and applications. IEEE transactions on neural networks and learning systems, 33(2), 494-514. https://arxiv.org/pdf/2002.00388.pdf%E2%80%8Barxiv.org 

Wang, Z., Zhang, J., Feng, J., & Chen, Z. (2014, June). Knowledge graph embedding by translating on hyperplanes. In Proceedings of the AAAI conference on artificial intelligence (Vol. 28, No. 1). https://ojs.aaai.org/index.php/AAAI/article/download/8870/8729 

Academic papers are really just a series of single meals within the greater academy of academic work. You have to really be committed to bringing together your overall thoughts on the field, the most relevant publications, and ultimately the totality of things happening in your field of academic study. You cannot for the most part hang your hat on any one academic paper being able to explain it all. Together with a multitude of other papers the content has more context. Sometimes people stop eating single serving meals to write introductions, textbooks, or other onramp materials to help people catch up. My fear has been that within the ML and AI spaces the flooding of content has made catching up almost impossible for people wanting to find the on ramp to getting up to speed on everything that is happening. This problem exists in different ways for researchers and scholars that are just trying to keep up with the endless stream of new content along the way. Every day, month, and year new papers are being published at rates that are mind boggling. Now that synthetic written content has gone mainstream thanks to ChatGPT kickstarting that marketplace. My honest guess here is that a lot of researchers will kickstart their writing endeavors with the rocket booster for written content creation that is ChatGPT. They can just edit it down and move along to publish more papers.

That preamble is super important to trying to contextualize why understanding the knowledge graph is so important. An important factor within the larger aggregate knowledge graph we all share itself is changing. It’s really like somebody showed up to the party and invited way more people than could possibly attend. Yeah, I’m about to talk about the effects of content flooding on future knowledge graph management. When the intake protocols for the knowledge graph cannot tell the difference between synthetically created input data and the standard product that has been on the market for thousands of years. For the most part knowledge graph based algorithms have had a hard time dealing with satire and sarcasm content where the author is intentionally spinning a false narrative. You end up with two conflicting next best answers where one should have a very low confidence score. However, this new effort within ChatGPT is whole-sale different. You have content that looks and seems like it should be included in the knowledge graph, but it is not tested or curated in any way shape or form. It’s almost like a point in time has to be considered where things before ChatGPT and things after ChatGPT have different weights within the overall knowledge graph. That is a troubling idea to consider. 

Top 5 Tweets of the week:

What’s next for The Lindahl Letter? 

* Week 111: Natural language processing 

* Week 112: Autonomous vehicles

* Week 113: Structuring an introduction to AI ethics

* Week 114: How does confidential computing work?

* Week 115: A literature review of modern polling methodology

If you enjoyed this content, then please take a moment and share it with a friend. If you are new to The Lindahl Letter, then please consider subscribing. New editions arrive every Friday. Thank you and enjoy the year ahead.

This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.nelsx.com