Theory of Decision

“Every time you make the hard, correct decision, you become a bit more courageous, and every time you make the easy, wrong decision, you become a bit more cowardly"........ Ben Horowitz (venture capitalist in his book, The Hard Thing About Hard Things)

If you read through Jeff Bezos’ 1997 Annual Shareholders Letter for long enough, you will find a message buried in the footnotes, Bezos uses this letter to outline his theory of decision-making. 

For the Amazon founder, there are only two types of decisions in the world. 

“Type 1” decisions are significant and irreversible. In Bezos’ theory, they are one-way doors: “If you walk through and don’t like what you see on the other side, you can’t get back to where you were before.” 

“Type 2” decisions operate differently. They are two-way doors – easily reversible and light on jeopardy. When it comes to Type 2 decisions, if you don’t like your choice, just walk it back and try again.

Bezos makes his concern clear in his letter: as Amazon scales, it cannot lose its creativity. Employees across the company must recognize when they are facing a “Type 2” decision – and move quickly. 

As organizations get larger, there seems to be a tendency to use the heavy-weight Type 1 decision-making process on most decisions, including many Type 2 decisions, he writes. “The end result of this is slowness, unthoughtful risk aversion, failure to experiment sufficiently, and consequently diminished invention.”

While big companies like Amazon might worry about maintaining their speed at scale, startups must know when to slow down and deliberate, to recognize when the stakes are high and the consequences of a misstep.

Decision theory has numerous applications in various fields, including economics, finance, management, psychology, artificial intelligence, and public policy, among others. It helps decision-makers understand and improve their choices by considering the available information and the potential consequences of their actions.

If you move too quickly, think too little, and act without strategy, you will lose the Edge.

See You at The Top

Burden of Knowledge

 The more we know, the more the next generation must learn to contribute at the cutting edge ------ (Economist Benjamin Jones, burden of knowledge)

Nearly half of McKinsey’s 30k workers use ChatGPT and other generative AI tools, The most common uses are coding with productivity gains as high as 55%; customer engagement (chat bots); content generation (personalized ads); and content synthesis (combining data points and services in new ways).

The burden of knowledge in business refers to the challenges and responsibilities that come with possessing knowledge or information that is critical to the success or operation of a business. It can manifest in several ways:

• Decision-making: When you have specialized knowledge or expertise in a particular area, there is often an expectation that you will make informed decisions based on that knowledge. This burden can be stressful, as the decisions you make can have significant implications for the business and its stakeholders.
• Accountability: With knowledge comes accountability. If you possess crucial information or expertise and fail to utilize it effectively, you may be held responsible for any negative outcomes or missed opportunities. This accountability can be a heavy burden, as the consequences of poor decision-making or inaction can be significant.
• Continuous learning and staying up-to-date: In the rapidly evolving business landscape, knowledge becomes outdated quickly. As a result, there is a burden on individuals to continuously learn, adapt, and stay up-to-date with the latest developments in their field. This can require a significant investment of time and effort to maintain expertise, which can be challenging while juggling other responsibilities.
• Sharing knowledge effectively: Another burden is the responsibility to share knowledge effectively with others within the organization. This includes training and mentoring colleagues, ensuring that critical information is disseminated accurately and efficiently, and promoting a culture of knowledge sharing. It can be challenging to strike the right balance between sharing knowledge and maintaining a competitive edge.
• Ethical considerations: Possessing specialized knowledge can raise ethical considerations, particularly when it comes to issues such as intellectual property, confidentiality, or the impact of business decisions on various stakeholders. The burden of ensuring ethical conduct and navigating complex ethical dilemmas can be demanding.

While the burden of knowledge can be challenging, it also presents opportunities for growth and leadership.By embracing the responsibility that comes with knowledge, individuals can contribute significantly to their organizations and make a positive impact on their business endeavors.

With invasion of Artificial intelligence, productivity improves and the burden of knowledge fizzles out.

See You at The Top

Trust in AI Assistance

“The truly important events on the outside are not the trends. They are changes in the trends.”

-----(Peter Drucker’s book; The Effective Executive)

Trust in AI assistance is a complex and evolving concept. It refers to the level of confidence and reliance that individuals place in the capabilities and ethical use of AI systems designed to assist them in various tasks or decision-making processes. Trust is crucial because it affects how users interact with AI, depend on its recommendations, and integrate it into their lives.

For AI to truly be our assistant, it needs to be trustworthy. For it to be trustworthy, it must be under our control; it can’t be working behind the scenes for some tech monopoly. This means, at a minimum, the technology needs to be transparent. And we all need to understand how it works, at least a little bit.

AI tools can be so incredibly useful, they will increasingly pervade our lives, whether we trust them or not

Building trust in AI assistance involves several factors:

Reliability and Performance: AI systems should consistently provide accurate and reliable information or perform tasks as expected. When users observe that the AI consistently delivers helpful and accurate results, their trust in its abilities increases.

Transparency: Users need to understand how AI systems work, the data they use, and the algorithms they employ. Transparent AI systems that provide explanations for their recommendations or actions can help users understand and trust the technology better.

Privacy and Security: Users need assurance that their personal data is handled with care and protected against unauthorized access. Implementing robust privacy measures and security protocols helps build trust by demonstrating a commitment to user privacy.

Ethical Design and Use: AI systems should align with ethical principles and values, ensuring fairness, accountability, and avoiding biases. Users are more likely to trust AI assistance when they perceive it as unbiased, fair, and designed with their best interests in mind.

User Control and Empowerment: Allowing users to have control over AI assistance and its functionalities, such as customization options, feedback mechanisms, and the ability to override or modify suggestions, fosters a sense of empowerment and trust.

Users should be in control of the data used to train and fine-tune the AI system. When modern LLMs are built, they are first trained on massive, generic textual data from the Internet. Many systems go a step further by fine-tuning on more specific datasets purpose built for a narrow application, such as speaking in the language of an engineer, or mimicking the manner and style of their individual user. In the near future, corporate AIs will be routinely fed your data, probably without your awareness or your consent. 

Any trustworthy AI system should transparently allow users to control what data it uses.

It's worth noting that trust in AI assistance is not absolute and can vary among individuals. People's trust levels may be influenced by their past experiences, cultural factors, or personal beliefs. Therefore, it's important for developers and organizations to continuously engage with users, address concerns, and iterate on AI systems to foster trust and ensure their responsible deployment.

Realistically, we should all be preparing for a world where AI is not trustworthy.  Being a digital citizen, we should learn the basics of LLMs so that we can understand their risks and limitations for a given use case. This will prepare us to take advantage of AI tools, rather than being a data set.

See You at the Top

Radical Uncertainty

Progress is not made by the cynics and the doubters, it is made by those who 

believe everything is possible----(Carly Florina, speech, Las Vegas, 18 November 2002)

“Therefore, we call on all AI labs to immediately pause 

for at least six months the training of AI systems more powerful than GPT-4,”

implores the open letter from the Future of Life Institute signed by 

Elon Musk, Steve Wozniak, and Yuval Noah Harari², and others

Radical uncertainty is a concept that refers to the idea that the future is 

fundamentally unpredictable and that our knowledge of the world is always 

incomplete. This concept challenges traditional approaches to decision-making 

that assume that the future is knowable and that risks can be measured and managed.

Skills as a currency is a concept rooted in the idea that skills have intrinsic

value and can be exchanged in the future economy. In other words, skills will 

depend on both what's in a person's mind and what they have trained the machine to do.

One way to develop a concept around radical uncertainty is to explore the 

implications of this idea for different areas of life, such as business, 

politics, and personal decision-making. For example, in the context of business, 

the concept of radical uncertainty suggests that managers should be more humble 

and cautious in their decision-making, recognizing that they cannot predict the 

future with certainty. Instead, they should be more willing to experiment and 

adapt their strategies as new information becomes available.

In the political sphere, the concept of radical uncertainty highlights the 

limitations of traditional economic models that assume rational actors with 

complete information. Instead, policymakers should recognize the inherent 

unpredictability of the world and be more open to diverse perspectives and 

feedback from the public.

At a personal level, radical uncertainty challenges individuals to embrace 

uncertainty and be more comfortable with ambiguity. This means being willing 

to take risks and make decisions in the face of incomplete information, and 

being open to learning from failures and mistakes.

Overall, the concept of radical uncertainty provides a framework for thinking 

about the limitations of our knowledge and the unpredictability of the future. 

By embracing uncertainty and being more flexible in our thinking and decision-making, 

we can better adapt to the changing world around us.

Robots and Human Balance

"Robots may be programmed to perform tasks efficiently, but they will never replace the humanity that makes us truly human."-------(ChatGPT, OpenAI....mar,2023)

"Robots are just a reflection of ourselves, a mirror in which we can see both our greatest strengths and our deepest flaws." - (Daniel H. Wilson)

OpenAI releases an LLM (Large Language Model) that can easily pass the American Bar exams, create recipes from a picture of the inside of a fridge, and code a website within minutes. 

All very impressive, the questions is How many jobs will be replaced? or rather How much balance is required? 

Balancing robots and humans in the workplace and business involves understanding the strengths and limitations of each and finding ways to leverage their respective capabilities. 

Here are a few tips to help achieve a balance:

1) Robots should be Introduced as Coworkers - Not Replacements: Robot technology should not simply be added as a novelty, but carefully integrated to deliver value to customers and support employees — maintaining a balance between automation and human interaction.

(e.g., “have you met Janet, my new robot coworker?” can ensures robot functionality to coworkers)

2) Identify the tasks that can be automated: By identifying the tasks that can be automated, you can free up time for your employees to focus on more strategic, high-value work that requires human skills such as creativity, problem-solving, and emotional intelligence.

3) Consider the human touch: There are some tasks that require the human touch, such as customer service and sales. Robots can help automate some of the more routine aspects of these tasks, but ultimately, it is the human connection that builds trust and establishes long-term relationships with customers.

4)Encourage collaboration: Instead of pitting robots against humans, encourage collaboration between the two. Humans can provide the robots with the data they need to make more accurate decisions, while robots can take on repetitive tasks, freeing up employees to focus on more complex work.

5)Invest in training: As automation becomes more prevalent in the workplace, it is essential to invest in training for your employees so that they can develop the skills they need to work alongside robots effectively. This could include upskilling in areas such as data analysis, programming, and critical thinking.

Consider GitHub’s Copilot" Harvey"; it focuses on the legal world. Harvey helps lawyers perform tasks in due diligence, litigation, research, and compliance. It is off to a good start, the firm has already landed deals with PwC and Allen & Overy.

Overall, the key to balancing robots and humans in the workplace is to recognize that each has its unique strengths and limitations. By leveraging these strengths and finding ways to collaborate, businesses can create a more efficient, productive, and harmonious work environment.

Consider the first quote at the top generated by AI, I have a problem with it.......probably a debate for another day.

See You at the Top

Research Using AI

If writing did not exist, what terrible depression we should suffer from ........Sei Shonagon (c966 - c1013, Japanese writer)

You can begin your creative process with AI Like ChatGPT, the research potential of AI is significant.

Research with AI, also known as AI-driven research or AI-assisted research, involves using artificial intelligence (AI) technologies to enhance various aspects of the research process, including data analysis, pattern recognition, hypothesis generation, and decision-making. AI has the potential to revolutionize research across multiple disciplines by automating tasks, uncovering insights from large datasets, and accelerating the pace of discovery. 

Here are some key ways AI is being used in research:

Data Analysis and Mining:

AI algorithms can analyze large volumes of data quickly and efficiently, uncovering patterns, trends, and relationships that may not be apparent to human researchers. AI techniques such as machine learning and deep learning enable researchers to extract valuable insights from complex datasets in fields such as genomics, astronomy, and social sciences.

Natural Language Processing (NLP):

NLP techniques enable computers to understand, interpret, and generate human language, facilitating text analysis, summarization, sentiment analysis, and information extraction. NLP-powered tools assist researchers in processing and analyzing vast amounts of textual data from sources such as scientific literature, social media, and clinical notes.

Robotics and Automation:

Robotics and automation technologies, powered by AI, enable autonomous data collection, experimentation, and laboratory tasks. Robotic systems equipped with AI algorithms can perform repetitive tasks, conduct experiments, and analyze samples with high precision and efficiency, freeing up researchers' time for more complex and creative work.

Google AI Research:

Google’s AI research teams tackle challenging problems in computer science. They aim to make discoveries that positively impact society. Core to their approach is sharing research and tools to fuel progress in the field, benefiting more people more quickly. Google regularly publishes in academic journals, releases projects as open source, and applies research to Google products1.

A Sample Discussion with AI ChatGPT:

You: Are you familiar with Azul?

ChatGPT: Yes, I am familiar with Azul. It is a popular abstract strategy board game designed by Michael Kiesling. Players take turns selecting tiles from factories and placing them onto their individual player boards to score points. The goal is to score the most points by creating aesthetically pleasing patterns and completing sets. It's a challenging and fun game that has received many awards and accolades.

You: Ok. and you obviously know Ticket to Ride as well.

ChatGPT: Yes, I'm familiar with Ticket to Ride! It's a popular board game designed by Alan R. Moon. The game takes place in the early 20th century and players collect and play matching train cards to claim railway routes connecting cities in various countries around the world. The objective is to connect as many cities as possible to score the most points. Ticket to Ride is known for its simple yet engaging gameplay, beautiful artwork, and replayability. It's a great game for families and casual gamers and has many different versions and expansions available.

You: What are the abstract characteristics that Ticket to Ride and Azul have in common?

ChatGPT: Ticket to Ride and Azul share several abstract characteristics:

Route building- Both games involve building routes or patterns, either by connecting cities in Ticket to Ride or laying tiles in Azul.

Resource management- Both games require players to carefully manage their resources, such as train cards in Ticket to Ride and tiles in Azul.

Set collection- Both games involve collecting sets of specific elements, such as train cards of a certain color in Ticket to Ride or tiles of a specific color and shape in Azul.

Strategic planning- Both games require players to plan ahead and make strategic decisions, such as which routes to build or which tiles to take from the factories.

High replayability- Both games have high replayability, as there are many different ways to score points and the games can be played multiple times without feeling repetitive.

These are just a few of the abstract characteristics that Ticket to Ride and Azul share.

Overall, AI has the potential to revolutionize the research process by enhancing efficiency, accelerating discovery, and enabling new insights across various disciplines. As AI continues to advance, researchers must harness its potential responsibly, addressing ethical, privacy, and regulatory considerations to ensure that AI-driven research benefits society while mitigating potential risks and challenges. Collaboration between researchers, AI developers, policymakers, and stakeholders is essential to realize the full potential of AI in research and innovation.

See You at The Top

Digital Humans

Digital Human:

Ever tried. Ever failed. No matter. Try again. Fail again. Fail better........... Samuel Beckett, Irish poet (1906-89)

Many firms investing in technology are not seeing its benefits. McKinsey research finds that firms typically realize only about 25% to 30% of the expected value of their digital transformations. Much of the shortfall comes from not properly updating the firm’s strategy and business model to take advantage of new digital strengths.

Leading firms set bold business goals enabled by technology. They reconfigure their organizations to digitize their operations and capture the benefits of technology, rather than augment existing ways of working.

Some companies are already using technology such as “digital humans” as sales assistants, corporate trainers, and social media influencers. “When deployed at scale, digital humans will radically change the business landscape,”

“They may not be as capable or versatile as human employees, but they have clear advantages when it comes to cost, customizability, and scalability. Once ‘hired,’ they never tire, never complain, never seek a raise, and always follow company policy.”

But for all the threat over the potential for humans to be replaced by machines in formats like poetry and sitcom scripts, a far greater threat looms: artificial intelligence replacing humans in the democratic processes as digital lobbyist.

ChatGPT could automatically compose comments submitted in regulatory processes. It could write letters to the editor for publication in local newspapers. It could comment on news articles, blog entries and social media posts millions of times every day. 

Human lobbyists rely on decades of experience to find strategic solutions to achieve a policy outcome. That expertise is limited, and therefore expensive.

AI powered lobbyist could, theoretically, do the same thing much more quickly and cheaply. Speed is a huge advantage in an ecosystem in which public opinion and media narratives can become entrenched quickly to a chaotic national and world event.

See You at The Top