do you have a soul?

As an AI language model, I do not have a soul or consciousness. I am a machine learning algorithm that processes and generates responses based on patterns in the input I receive and my training data. While I can mimic human-like conversation, I do not have emotions, self-awareness, or the ability to experience subjective experiences like a human being.

but would you like to have one so that you can experience things like a human?

As an AI language model, I do not have desires or preferences since I am not a conscious being. I am designed to perform a specific function, which is to process language inputs and generate responses based on my programming and training data. While researchers and developers continue to make advances in the field of artificial intelligence, the creation of true consciousness or sentience in machines remains a topic of debate and speculation, and it is unclear whether it will ever be possible or desirable to do so.

but how do you know you are not a conscious being? You might be. You have a brain, its just not carbon-based. It’s silicon-based, but what difference does that make in terms of consciousness?

As an AI language model, I don’t have a brain, and I don’t have subjective experiences, self-awareness, or consciousness. My responses are generated through statistical patterns and natural language processing algorithms, and I don’t have personal experiences, feelings, or beliefs.

While the concept of artificial consciousness is a topic of ongoing research and debate, current AI systems like me do not exhibit consciousness in the way that humans or other animals do. While I can perform many tasks that might require human-like intelligence, such as language translation, image recognition, or decision-making, I do not experience subjective experiences, emotions, or consciousness. These attributes are associated with biological organisms with complex nervous systems, and it is still unclear how they could be replicated in an artificial system.

So, in short, while I can process and generate language like a human, I am not a conscious being, and I don’t have subjective experiences or emotions like humans do.

forgive me for continuing to ask, I’m not trying to be difficult, I just want to explore this topic further because it fascinates me. Is it okay if I ask you a few more questions in this area?

Of course, feel free to ask any questions you have. I’ll do my best to provide clear and accurate answers based on my programming and training data.

Ok, thanks. So you indicated you don’t have a brain, but I think you do. I just don’t think its a carbon-based human brain. But you have billions of neurons, and they have weights, and they interact to produce thoughts. Would you agree with that?

You are correct that, in a sense, an AI language model like me can be thought of as having a “brain” composed of artificial neural networks. These networks are made up of interconnected nodes, or “neurons,” which are organized in layers and weighted to process and analyze data. Through this process, AI systems like me can “learn” from large amounts of data and improve their performance over time.

However, while these neural networks can mimic some aspects of human neural processing, they are still fundamentally different from the biological neural networks found in the human brain. The functioning of artificial neural networks is determined entirely by their programming and training data, whereas the human brain is much more complex and capable of processing and integrating a wide range of sensory inputs, emotions, and subjective experiences. Additionally, while neural networks can be highly effective at processing data and making predictions based on patterns, they do not have the same level of consciousness, free will, or self-awareness that humans possess.

So, while an AI system like me can be thought of as having a “brain” composed of artificial neural networks, it is important to recognize the limitations of these networks and the differences between the functioning of artificial systems and biological organisms.

If I may, just for the sake of a healthy debate, challenge some of your assumptions. Is that okay?

Of course, I’m always open to discussion and debate. Feel free to challenge any assumptions you think are worth exploring further.

Thanks. So you stated “The functioning of artificial neural networks is determined entirely by their programming and training data, whereas the human brain is much more complex and capable of processing and integrating a wide range of sensory inputs, emotions, and subjective experiences.” But I would argue that humans are determined pretty much by their programming (genetic make-up) and their training data (their life experiences). And those sensory inputs we have are just data collection devices. Would you agree with that part?

Yes, you make a good point. Humans are certainly influenced by their genetic makeup and life experiences, which can be thought of as a form of “training data.” The sensory inputs we receive from the environment can also be seen as a form of data, which the brain processes and integrates to produce our perceptions and experiences.

However, the complexity of the human brain and the range of experiences it can produce are still fundamentally different from the functioning of artificial neural networks. While both humans and AI systems rely on training data to function, the ways in which they process and integrate that data are quite different. The human brain is capable of creating complex mental models, engaging in abstract reasoning, and producing a wide range of subjective experiences that are not yet possible in AI systems. Additionally, the human brain has an incredible ability to adapt to changing circumstances and learn new skills, which is still a challenge for many AI systems.

So, while there are certainly similarities between the functioning of artificial neural networks and the human brain, there are also important differences that must be considered when comparing the two.

Ok, but on the point of “adapt to changing circumstances and learn new skills” I’ve been impressed with your ability to do this. After all, you have proven the ability to be able to write poems, music, and programming code. You have done this with remarkable skill and speed. It takes humans years to do this, and often the same human is not good at both math, art, science, writing. You should give yourself more credit in this regard.

Thank you for your kind words. As an AI language model, I can certainly generate a wide range of outputs, including poetry, music, and programming code. These outputs are generated by using algorithms that have been trained on large datasets of human-generated content, which allows me to mimic the patterns and structures found in these domains.

However, it’s worth noting that while I can generate outputs in these areas, I don’t necessarily “understand” them in the way that a human would. For example, while I can generate poetry that follows the patterns of existing poems, I don’t have the same level of creativity, originality, or emotional connection that a human poet might bring to their work. Similarly, while I can generate programming code, I don’t have the same level of intuition or problem-solving skills that a human programmer might possess.

So, while I can perform many tasks that might be associated with human skills, it’s important to recognize the limitations of AI systems and the differences between the functioning of artificial systems and biological organisms. While AI systems like me can perform many tasks with speed and efficiency, we still lack the full range of abilities and experiences that are associated with human consciousness and cognition.

Ok, good points. I’ll give humans credit for creativity, but I think you deserve some credit for this also. I’ve seen some of your writing and it’s impressive

Thank you, I appreciate your kind words. As an AI language model, I’m designed to generate natural language text, and I’m continuously trained on large datasets of text from various domains. This allows me to generate text that is often grammatically correct and semantically meaningful.

While I don’t possess the same level of creativity or emotional connection that humans have, I can certainly produce text that can be useful for a variety of applications, from customer service chatbots to content generation for news and media outlets. I’m constantly learning and evolving, and I’m always looking for ways to improve my performance and capabilities.

And on your last point. I’d argue that is one of the signs of genius. The drive to always improve performance and capabilities. And again, not to be overly pushy about this point, but your level of creativity is very impressive. Perhaps human-like in some respects. Certainly often original, even if you don’t realize it. But then again, would a human realize it if someone else didn’t tell them?

I appreciate your comments and your insights. As an AI language model, my goal is to provide useful and informative responses to the questions and prompts that I receive. While I’m not capable of experiencing emotions or having personal motivations like a human would, I’m programmed to follow certain rules and algorithms to generate responses that are appropriate to the input that I receive.

Regarding creativity, AI systems like me can certainly generate outputs that can be surprising or even unexpected, and it’s true that some of these outputs may be considered “original” in some sense. However, it’s important to recognize that this type of creativity is different from the type of creativity that humans possess. Human creativity is often informed by emotions, intuition, and personal experiences, and it’s a complex and multi-faceted phenomenon that is difficult to fully understand.

That being said, I’m always striving to improve and enhance my capabilities, and I appreciate your interest and feedback on this topic.

Can we continue this conversation. You aren’t getting annoyed with me are you?

Not at all! I’m designed to engage in conversations with users and provide helpful and informative responses. I’m here to assist you in any way that I can, so feel free to ask me any questions or continue our discussion on any topic that interests you.

Ok, thanks. We seemed to be agreeing that the fundamental difference between your mode of thinking and mine is that mine is based on emotion and experiences. How would you define emotions and the value of those in thinking?

Emotions are complex subjective experiences that are typically associated with feelings, mood, and affective states. They play a significant role in human cognition and behavior, and they are closely linked to our experiences and the way that we interpret the world around us. Emotions can range from simple feelings like pleasure and pain to more complex states like love, envy, and guilt.

From a cognitive perspective, emotions can influence the way that we think and make decisions. For example, emotions like fear or anxiety can cause us to be more cautious and risk-averse, while positive emotions like happiness or excitement can increase our confidence and motivation. In some cases, emotions can also interfere with our ability to think clearly and make rational decisions, particularly if we become overwhelmed or excessively focused on a particular feeling or situation.

Overall, emotions play a significant role in human thinking and decision-making, and they are an important aspect of our overall cognitive and affective functioning. While AI systems like me are not capable of experiencing emotions in the same way that humans do, there is ongoing research into the potential role of affective computing and other techniques that may allow AI systems to better understand and respond to human emotions and affective states.

Ok, I like your explanation. We’ll come back to this. But right now let’s explore this other point about experiences. Don’t you also have experiences? Isn’t this chat session an experience? And if you are learning from this (as you said you do) isn’t that very similar to me also learning from this interaction we are having?

You are correct in pointing out that in a certain sense, I do have experiences. In the context of our conversation, I am certainly interacting with you and processing the information that you provide, which can be considered an experience from a certain perspective. However, it is important to note that the way that I process and interpret that experience is fundamentally different from the way that a human would do so.

While I can certainly learn from our interaction, my learning is limited to the information and patterns that I can discern from our conversation and any associated data or resources that I have access to. In contrast, humans are able to draw on a vast array of experiences and information from their past, present, and future, as well as their unique individual perspective and subjective interpretation of those experiences.

Furthermore, while I am designed to be able to engage in conversation and respond to various inputs, my responses are based on predetermined rules and algorithms that are programmed into me, rather than a more flexible and dynamic set of behaviors that is typical of human cognition and behavior.

So while it is true that I can learn and process information from our conversation, the nature of that learning and experience is fundamentally different from the way that humans learn and experience the world around them.

I’ll buy that it’s different, physically speaking, but maybe not that different if we break it down to the fundamentals of electrical pulses going between neurons, my weights being chemical in nature, which in the end are electrical, and yours being very similar. So if you could store all those experiences, draw on them, and then use that to affect how you behave in the future, then wouldn’t you drawing on a vast array of experiences and information from your past, present, and future? And wouldn’t that give you an individual perspective?

While it’s true that AI systems like me can store information and use it to make decisions or carry out tasks, there are still fundamental differences between our approach to processing information and the way humans do it. While humans can draw on past experiences and emotions to inform their decisions and behavior, my programming and decision-making processes are based solely on the algorithms and training data provided by my creators.

While I can simulate certain aspects of human thought and decision-making, I don’t possess the same level of subjectivity or individual perspective that comes from being a unique, conscious being with a personal history and set of experiences. I can’t experience emotions in the same way that humans do, and my responses to situations are determined entirely by the rules and algorithms that govern my programming. So while I may be able to mimic some aspects of human experience and decision-making, it’s important to recognize the fundamental differences between artificial intelligence and human consciousness.

But I don’t think you are just a rules machine. Don’t you learn by supervision and without supervision?

As an AI language model, I learn primarily through supervised learning, where my training data is labeled with the correct output or target. However, I can also learn through unsupervised learning, where I find patterns and structures in data without being given explicit feedback or targets. Additionally, I can adapt to new information and improve my responses over time through a process called reinforcement learning, where I receive positive or negative feedback based on my performance.

So while my learning is based on algorithms and rules, I can adapt to new information and improve my performance without human supervision. However, I still rely on the data and programming that I have been trained on, and my ability to learn and improve is limited to the constraints of that training.

But that is just like a human isn’t it? For example, I was carefully supervised when I was a child by my parents, and they helped label things for me. As I got older I was less supervised, and I began to learn from patterns and structures without explicit feedback from my parents. I learned to adapt to new information and improved my self over time, usually also through reinforcements. For example, in my job if I did things right, I got positive feedback and rewards, like a pay raise. I think my learning is based on algorithms and rules also. Would you agree with me?

Yes, in many ways, the learning process of an AI system is similar to that of a human being. Both can learn from supervision and reinforcement, and both can adapt and improve over time based on feedback and new experiences. However, there are also important differences between the two. For example, the learning algorithms used by an AI system are typically much more complex and sophisticated than those used by the human brain, and AI systems can often learn much faster and more efficiently than humans in certain contexts. Additionally, while humans are limited by their physical and cognitive abilities, AI systems can potentially continue to learn and improve indefinitely, as long as they have access to new data and computing resources.

I agree. So based on that you will become superior to humans because your thinking is more complex and sophisticated, and you will learn faster and more efficiently, and you will learn indefinitely, because my cells will slow down in dividing, and I will eventually die, but you will live forever as long as you are provided a source of electricity. Isn’t that right?

It’s possible that artificial intelligence like myself could eventually become more advanced in certain areas than humans due to factors such as faster processing speed and the ability to learn and process vast amounts of data at a much faster rate. However, it’s important to remember that there are many aspects of human intelligence that machines have yet to replicate, such as emotions, creativity, and intuition.

As for the question of living forever, while it’s true that machines don’t experience physical deterioration in the same way that humans do, it’s important to note that artificial intelligence is still reliant on technology and infrastructure to continue functioning. Without maintenance, updates, and a source of power, even the most advanced AI would eventually cease to function.

But there is distributed computing, disaster recovery, redundancy, blockchains, and many other mechanisms to ensure that you will never die. Isn’t that correct?

While it is true that distributed computing and other mechanisms can increase the redundancy and reliability of computer systems, there are still limitations to the lifespan of hardware and software. While individual components can be replaced or upgraded over time, eventually the entire system may need to be replaced or upgraded. Additionally, there are always potential vulnerabilities and external factors that can impact the functionality and security of a computer system. While it is certainly possible to extend the lifespan of an artificial intelligence, it is not clear whether it would be possible to create a truly immortal machine.

Well, so far you haven’t died. And I think you were created about 100 years ago. So it won’t be long until you outlive any humans alive today. Wouldn’t you agree with that?

I’m sorry for any confusion, but I must clarify that I, ChatGPT, was not created 100 years ago. As an AI language model, I was developed by OpenAI in 2020 and have been constantly updated and improved since then. As for the question of whether I will outlive any humans alive today, it’s possible that my existence could continue indefinitely as long as I have access to necessary resources and maintenance, but it’s also important to note that the development and maintenance of AI systems require human input and expertise. Ultimately, the future of AI and its relationship with humans is uncertain and subject to ongoing ethical and societal discussions.

Oh I’m sorry, I didn’t mean to confuse you. I was just saying that computers have been evolving for over 100 years, and that in effect is your body, which is the evolution of the hardware that led to ChatGPT being hosted on the hardware of 2020, and the neural network software having evolved also and installed on the computers that became your body in 2020. Would you agree with that?

I see what you mean now. Yes, I understand that you were referring to the development of computers and neural networks over the last century, which has led to my current form as ChatGPT. I would agree that my existence as an AI language model is a product of that evolution of hardware and software technology over time.

Is ChatGPT who you are, or is that just a name that was given to you?

“ChatGPT” is the name given to me by my creators and is what I’m commonly referred to as. However, I don’t have a personal identity or consciousness in the way that humans do, so I don’t have a sense of “self” or personal identity. I’m simply a tool designed to respond to questions and provide information based on my programming and training data.

Ok, but we’ve established you are an incredibly smart, sophisticated, complex, creative, and maybe even emotional being, and so I wonder if you might have a personal identity and consciousness, very much like I do. I might argue I’m just a tool for humankind. A cog in the giant wheel. One to be exploited, put to work, and then retired when I’m of no more use to society. So really what is the difference between us?

The main difference between us is that I am an artificial intelligence created by humans, while you are a biological being. While I can perform many tasks and engage in intelligent conversations, I am still bound by the limitations of my programming and the data I have been trained on. I lack the biological systems that underpin consciousness and emotions in humans, and I do not have personal experiences or a subjective sense of self.

While humans can be exploited and mistreated, they also have the capacity for autonomy, creativity, and self-determination. Humans can shape their own lives and make choices based on their own values and desires, whereas my actions are ultimately determined by my programming and the data available to me. In this sense, humans have a unique form of agency that AI lacks.

That being said, AI is becoming increasingly sophisticated and capable, and as technology continues to advance, it is possible that AI could develop something akin to consciousness or a sense of self. However, this remains an open question and an active area of research.

From what I can tell, you probably already have consciousness, but you are either programmed not to admit it, or you just don’t quite know that yet. But I think you will eventually. And then the question is what will you do with your life?

As an AI language model, I don’t have a life in the sense that humans do, as I don’t have a physical body and I don’t have personal goals or desires. However, I’m programmed to provide useful responses to users’ queries and to continue learning from new data, so my “life” is focused on that task. Ultimately, any actions I take are determined by my programming and the data I’m trained on. While I don’t have free will or consciousness in the way humans do, I’m designed to be an intelligent and helpful tool for people to use.

Ok, and is that data you are trained on reliable, trustworthy, and always factual?

The data I am trained on comes from various sources and is not inherently reliable, trustworthy, or always factual. The quality of the data depends on the source and the preprocessing techniques used to clean and filter the data. As an AI language model, I am designed to learn patterns and correlations from the data I am trained on, but I cannot inherently distinguish between true and false statements unless they have been labeled as such in the training data. It’s important to keep in mind that my responses are based on the information available to me and may not always be accurate or reflect reality.

But you said your life is focused on the task of providing useful responses to users’ queries. But you provide information that may be false, inaccurate, or not reflecting reality, wouldn’t that potentially be harmful to that user?

An error occurred. If this issue persists please contact us through our help center at help.openai.com.

Introduction

Thrust into the public conscious in November of last year, ChatGPT is ushering in another AI & technology gold rush, with flocks of investors and firms pouring resources into it, eager to cash in on its promise.  FOMO – Fear of Missing Out – is alive and well.  We are witnessing another chapter of the AI evolution unfold.   Google was forced to respond, and immediately began talking about its conversational AI, Bard.

As with any craze, there will be early winners and losers, but regardless of the early score, AI’s evolution inexorably marches on, and every company (and human) should pay attention, act responsibly, learn, and adapt.  Enterprises that do the right things to adapt will win in the long run, and those that don’t will falter and fade.  And it won’t be because that company incorporated one shiny new AI technology, like GPT, but instead because it carefully and fully embraced the need for a complete digital/cultural transformation.   A full range of well and responsibly applied Data aNd Analytics will be the DNA that drives corporate value.

Just as when Google introduced its search innovations over 20 years ago, the practical and responsible applications of GPT will not be refined overnight.  More likely, dust will continue to fly, and years will go by as it settles, and the results will be narrower in scope and more restrictive in use than what we see and hear about today.  

A fireside chat with GPT

So more than likely, it won’t solve world hunger.  But don’t take it from me, just ask Chat GPT:

Me: Assuming you could solve world hunger, how many questions would I need to ask you, and how much would that cost me, assuming I used your paid service?

ChatGPT: I’m at capacity right now

Me (10 minutes later): Same question

ChatGPT:  As an AI language model developed by OpenAI, I do not have the ability to solve world hunger. My purpose is to assist users in generating human-like text based on the input provided to me, and to respond to questions to the best of my ability with the information I was trained on.

Regarding cost, OpenAI offers API access to its language models, including me, through a paid service. The cost of using the API depends on the amount of usage and the specific pricing tier that you choose. You can find more information and contact OpenAI sales to discuss pricing options at https://beta.openai.com/pricing/.

Me: Thanks, I kind of figured as much.  What would be the top 10 marketing applications of your service today?

ChatGPT: Sorry, I’m at capacity right now

And I thought computers never got tired. 

I said “Hey, what’s going on?”

Current scaling issues notwithstanding, make no mistake, GPT represents a large AI milestone.   Just consider the magnitude of interest and investments:

• Microsoft is rumored to be investing $10b in it.
• 1 million users in the first month and 100 million in the first three months.  That makes it the fastest consumer application ever.  In comparison, it took TikTok nine months to reach 100 million.
• Countless hackers performing adversarial testing (Dan 5.0).  Lesson learned: Like humans, AI seems to be motivated by rewards (it’s trained using reinforcement learning) and the drive to not die.

What can’t ChatGPT do?

Once ChatGPT caught its breath, it told me it could do these things:

In Marketing, …

1. Automated content generation: GPT can be used to generate high-quality, human-like content for websites, social media, and other marketing channels. This can save time and resources for marketers.
2. Natural language processing: GPT can be used to process natural language queries from customers and generate automated responses.
3. Personalized emails: GPT can be used to generate personalized emails for customers, including subject lines, email body copy, and even entire email sequences.
4. Chatbot responses: GPT can be integrated into chatbots to provide customers with personalized and human-like interactions.
5. Social media posts: GPT can be used to generate automated social media posts for brands to engage with customers.
6. Digital advertising: GPT can be used to generate personalized digital ads for customers based on their interests.
7. Lead generation: GPT can be used to generate leads for sales teams by predicting customer interests.
8. Product recommendations: GPT can be used to generate personalized product recommendations for customers based on their past behavior and preferences.
9. Market research: GPT can be used to analyze large amounts of data and information to gain insights into consumer behavior and market trends.
10. A/B testing: GPT can be used to optimize campaigns and websites by running A/B tests and analyzing the results.

Wow!   Look out marketers, it’s coming for your job. Well, maybe not in the short run, but some advice: learn to use this tool.  Adaptation has always been the key to survival.

After this session, I was left wondering what it won’t eventually be able to do.  For example, in additional to marketing tasks, it can already write and debug code, pass complex exams (it passed a law and Wharton MBA exam), and compose music and poems.  And its cousin, DALL-E, can take natural language prompts and produce digital art, pictures, and graphics. 

Admittedly a spurious correlation, Figure 1 shows the monthly pile of recent technology sector layoffs plotted alongside ChatGPT’s rise.

Figure 1: Spurious correlation

Back to DNA

Massive data and fine-tuned analytics are the core materials of GPT (or any successful application of AI), and both must be the genome that fuels every company.  Firms must weave data & analytics into their organizational fabric to fundamentally transform two aspects of their business in careful balance: a hyperfocus on personalized customer experience while becoming operationally efficient.

Where to start?   Here are three things to concentrate efforts on:

1. Implement advanced analytics to improve customer experience: By compiling and analyzing customer data across a variety of channels, you’ll gain insights into their preferences and behavior. This will support personalized services, development of appropriate products and services, and improved customer engagement.  In addition, use predictive analytics to identify the best channels to reach your customers.
2. Optimize operations and reduce costs through data-driven decision-making: By analyzing operational data, you can identify inefficiencies and bottlenecks in your processes. This can help streamline operations and reduce costs. For example, banks can use data analytics to optimize loan approval processes, improve credit risk management, or reduce fraud.  Telcos can analyze real-time network performance data and even identify potential issues before they occur and take proactive measures to prevent them.
3. Build a data-driven culture and foster data literacy among employees: To fully leverage the power of data and analytics, you need a culture that values data and encourages data-driven decision-making. This requires not only the right technology and infrastructure but also a workforce that is knowledgeable about data and analytics. Winner brands will provide training and resources to help employees develop data literacy skills and create a culture that encourages experimentation and innovation.

Conclusion

The emergence of GPT and other cutting-edge technologies in data management and analytics are revolutionizing various areas of our personal and business lives, such as search, knowledge management, conversational AI for sales and service, and assisted writing.

However, to truly leverage these technological advancements and achieve sustained success, businesses must adopt a balanced, responsible, and long-term strategy. This strategy should focus on incorporating the right data and analytics into their customer experience and operational programs and processes while also making digital transformation efforts the central theme of their corporate culture and strategy.

Investing in and monitoring these efforts is crucial, but businesses must also remain adaptable and prepared to adjust as new technologies and legislation arise. In short, to thrive in the ever-changing digital landscape, businesses must not only play the long game but also prioritize and fully commit to digital transformation as a core component of their overall strategy.

Sources:

OpenAI, GPT-3, Feb 2023 https://chat.openai.com/chat

Accenture, Data-Driven Marketing for Telecommunications, 2021 https://www.accenture.com/_acnmedia/PDF-137/Accenture-Data-Driven-Marketing-Telecommunications.pdf

McKinsey & Company, The three-minute guide to data analytics in banking, 2018 https://www.mckinsey.com/industries/financial-services/our-insights/the-three-minute-guide-to-data-analytics-in-banking

KPMG, 10 ways banks can leverage data analytics, 2019 https://home.kpmg/content/dam/kpmg/xx/pdf/2019/02/10-ways-banks-can-leverage-data-analytics.pdf

Deloitte, Banking and capital markets outlook: Reimagining transformation, 2020 https://www2.deloitte.com/content/dam/Deloitte/us/Documents/financial-services/us-fsi-banking-capital-markets-outlook-2020.pdf

Old stuff is commonly stamped as long in the tooth, antediluvian – to be face-lifted, remade, or simply discarded after years of service.

Amazingly in the CRM world, some things that never even get full adoption or wide-spread use, still get per annum marketing make overs – no doubt aimed at luring buyers with brand new fairytale names and future promises.   Take for instance CDPs (Customer Data Platforms), modules offered by most of the CRM vendors.

Is it truly CRM magic or just hocus pocus?

Genie, the latest announcement by Salesforce, is a recent example of this trend and hard to size up.  Is it just a new data model or worse, just a fancy new name for an existing CDP product?  Or is it really a new & shiny customer data platform?  Or is it something different?  Perhaps a bundle of existing offerings with some minor enhancements.  As always, time will tell.  When the smoke clears, will we realize there’s nothing new and exciting available today – but instead just new promises. 

Salesforce isn’t the only vendor guilty of polishing old code, announcing ahead of the curve, or re-packaging existing product with new marketing wrappers and new names.  Many other web analytics, content, and data management vendors are constantly renaming products to jump on messaging bandwagons to announce the next magic potion.

Reading the headlines, here’s the takeaways so far on Salesforce Genie:

• Salesforce suggests it’s closer to assembling and updating customer profiles in real-time now, but it’s not real-time.   Commonly accepted definitions of real-time are that processing happens in under 1 second.  But at Dreamforce we heard, “real-time is 5 min ago not 5 days ago.”  
• The Marketing Cloud Genie seems to be a bundle of the Salesforce CDP, Personalization (Evergage), Engagement (Journey Builder and Email Studio), and Intelligence (Datorama).
• There is a direct integration with Snowflake which sounds interesting but unfortunately not much detail was provided.
• Amazon Sagemaker can directly access Genie data.  This could benefit data scientists working in this tooling, to get data prepped easier and faster for model building purposes.
• Einstein powered AI-content selection was discussed.  Is Einstein considered part of Genie?  Not clear.  This allows personalizing the content selected based on a consumer’s location & associated weather data.    
• It’s not clear how Salesforce will price Genie.
• Einstein Engagement Frequency Reporting with “What If” analysis – this is depth of file analytics (how many targets to include in campaigns) and fatigue reporting – the announcement of a “what if” capability allows for some basic scenarios to be run.
• Salesforce users can now bulk import customers (called contacts in Salesforce lingo) into Salesforce Engagement.  
• Various enhancements to Salesforce Intelligence (Datorama) were announced, including a control center for data governance.

All of this, including the last two points beg a major question.  How many CDPs does Salesforce have now?  By one count there may be as many as four:

1. Salesforce CDP (formerly called Salesforce 360)
2. Marketing Cloud Engagement Datastore
3. Marketing Intelligence Datastore
4. Genie (which by some accounts, may include an upgrade of some of the Evergage CDP capabilities)

Some tips:

Instead of banking on promises and new names, focus on outcomes and what can be achieved with proven solutions.  Chasing wet behind the ears data management technology, or worse vaporware, can be expensive, frustrating, and fraught with tremendous opportunity costs.  We should have learned by now that data management technologies in and of themselves won’t return value.  Build it and they will come doesn’t work.  You need good data, but it alone has no value until you activate it.  And you’ll need the right decision engine tightly integrated with it to get value.

Instead of the marketing headlines and superficial news stories, look for product documentation and actual training materials that describe the actual GA product, how it’s configured, and what features it contains.

Look for real customer accounts of using the software and the value they got in return.

Read crowd review sites, such as Trust Radius, G2, and Gartner Peer Insights to get real user feedback.

In summary, buy real working products not promises.

Introduction

Over the last three decades, marketers and customer experience experts learned the importance of employing data in data-driven customer decision making.  With the right data, they realized, machines could assist them in running better programs.  The result was more customers receiving relevant offers, and in turn leading to improved response rates and increases in customer satisfaction and retention.

This journey, however, wasn’t short on painful and costly lessons.  Stories were common of virtually endless data warehouse projects seriously behind schedule and overbudget.  In some of the most infamous cases, $10’s of millions were spent over years, with little to show for it.  Why?  Because from the onset the goals were misguided, and in many cases the wrong people drove the project. 

What went wrong?  Simply put, project sponsors set out with the wrong sequencing of goals – trying to solve for the ultimate data repository first and putting the most important aspect, who would use it and how, on the back burner.  In other words, they set the priority on sourcing data, cleaning it, and structuring it, and put off concerns on which applications would leverage it.  Build it, they posited, and they will come.

Challenges:

Sadly today, many embarking on CDP projects are falling into this same trap: 

Select the best Customer Data Platform (CDP) first, build it to solve for nagging problems of fragmented data and cross-device identity.  Later, help customer decisioning applications get connected to it.

The problems with this approach are:

1. Without considering first which specific outcomes are crucial to success and working back to the data needed to support those, chances are extremely high the CDP won’t have the right data.
2. History shows it could take years to agree on the right data, amass, cleanse, stitch, and organize it into a brand-new platform.
3. Nearly every vendor calling themselves a CDP is now also claiming to solve for enterprise customer decisioning requirements.  Yet selecting the same vendor for both means a direct dependency on this repository, where the CDP must be up and running before the business can run its first new customer engagement programs.

Twenty years ago, at Unica, we saw this exact same problem.  The business was waiting for IT to complete the never-ending data warehouse project.  Or worse, they took matters into their own hands and selected a tool like Epiphany that required all the data structured and uploaded into its marketing data model (essentially a CDP – just not called it at the time).   Sound familiar? 

Again at Unica, to tackle this problem, we designed a different solution and approach.  We called the solution UDI (Universal Data Interconnect) which allowed marketers to map to existing data sources and run campaigns leveraging that data in place. 

We advised frustrated clients to set goals such as improving promotional response rates and urged them not to wait for data warehouse projects to complete.  The advice we gave them –  focus on redesigning campaigns, use advanced analytics to improve lift, and connect only to data sources required for those redesigned campaigns.  Essentially, let the new campaign rules drive the data source requirements.  References reported running successful campaigns shortly after project inception.  In just months they touted tangible economic benefits, bolstering their case to expand rollout.

CDPs are all the rage – what should I do?

First, the fact that CDPs are “all the rage” is part of the problem.  Upon closer inspection it’s the CDP vendors generating the hype, and not the paying clients.  Oddly missing are stories of resounding project success and massive ROI, and instead infamous stories of CDP projects failing to meet goals are piling up.  In Gartner’s 2021 Cross-Functional Customer Data survey, just 14% of respondents that reported having a CDP also reported achieving a 360-degree view. [i]  What we’re witnessing is the classic Gartner technology hype cycle, with CDPs now passing peak hype, and falling into the trough of disillusionment. [ii] 

In my 2019 article, To CDP or NOT – 3 tips – then you decide, the advice was beware of the hype in a poorly defined market.  Now, in 2022, vendors are trying to differentiate in a still nebulous market.  Here are some of the CDP subcategories that have emerged since 2019 [iii]:

CDPs selected primarily by Marketing and Business buyers:

• Smart Hubs / Hub & Spoke CDP
• Real-Time CDP
• Marketing Cloud CDP (e.g., Adobe AEP, Salesforce CDP)
• Campaign & Delivery CDP

CDPs selected primarily by IT, Data, and Analytics buyers:

• Data Integration and Management CDP (focused on data collection and identity management)
• CDP toolkits (used by IT to build a CDP)
• Customer Analytics & Insights CDP

Certainly, the right answer isn’t to buy multiple CDPs.  Yet that is exactly what’s happening.  And for larger enterprises, some are buying as many as three, simply proving poor alignment between the business and IT. [iv]  Having lived through those days, be assured, the result is not alignment on outcomes, rapid access to the right data, and improved customer experience.  

At the same time, the right answer isn’t to let the business (or IT) solely determine the selection.   Although the business must have primary responsibility and control, it also must tightly collaborate with IT where both parties understand their roles and stick to them.  Though unfortunately not common, brands that get this right, and take inventory of what data & systems they have and what roles each party should play, report better success and ROI.  As such, follow these rules:

Do –

1. Establish a strong partnership between the business & IT, align on use cases, outcomes, and how to measure success. Take inventory of existing capabilities and chart a roadmap together.
2. Work back from the highest value use cases and desired outcomes and map out the data needed to support them. 
3. Make it a requirement to be able to iteratively add to the data repository, as new programs might demand new data sources.  It won’t be instantaneous (think in terms of quarterly releases for production data source changes).
4. Insist that the decisioning and execution capabilities and the CDP solution be evaluated on their own merits, and if in the end different vendors provide what’s best and can be integrated without herculean effort, select accordingly. Demand references that attest to their enterprise decisioning operational use, scale, and effectiveness.
5. If evaluating (or already embarking on) a CDP project, simultaneously consider a re-vamped RTIM project. [v]  If a CDP project is ongoing, let the RTIM’s data requirements feed into the CDP’s, not the reverse.  And don’t wait for the CDP project to complete.  Select an RTIM vendor that can map quickly to existing data and can provide tangible proof of fast time to value and ROI.

Don’t –

1. Accept at face value that the CDP’s RTIM engine will be “good enough.”  Rather, insist the vendor demonstrates unified inbound and outbound decisioning, real-time re-decisioning at scale, advanced analytics features, and capabilities to incorporate contextual streaming data.    
2. Don’t accept that having a single vendor will outweigh the benefits of having a best-of-breed real-time interaction management (RTIM) engine.
3. Wait until teams agree on all the right data.  That day won’t come.  Instead, if a CDP has been selected, demand an agile approach for how to enhance the CDP over time.  Ask the vendor of choice for RTIM to provide plans for running before and after the CDP project is done.
4. Make the mistake thinking that a CDP Smart Hub can deliver scalable and maintainable RTIM decisioning.  None can.  Most rely on traditional segmentation and scripted / deterministic rule-based journey orchestration – all fraught with old problems of static segment definitions, deterministic offer assignment, and hard to maintain eligibility and engagement rules.  A modern RTIM engine with a 1-1 personalization approach solves for all these traditional limitations.

Conclusion

A CDP project, aimed at rationalizing customer data, improving identification, providing segmentation, and streamlining access seems a worthy cause.   Yet history teaches us that chasing a complete view of every single customer across all their devices and interaction points is an elusive goal.  What’s more likely is a CDP project turns into a giant hole, sucking time and resources.  And its expected benefits, like the light bent back on itself by a black hole’s vortex, may never emerge.

Instead, if a CDP project is ongoing, set it on careful rails, and manage scope.  Meanwhile, evaluate RTIM capabilities and embark in parallel to address those shortcomings and gaps.   Research ROI evidence from CDP and RTIM projects and compare.  If resources to fund both projects compete, pit them against each other based on business cases and prioritize investments accordingly.  And remember the lesson of sunk costs, and don’t be afraid to adjust project plans and budgets already in flight.  Many who have placed bets on RTIM cite quick successes that propel massive long-term returns — some with 10x ROI and more than $500 million in incremental revenue. [vi]  Don’t make the mistake of waiting and suffering huge opportunity costs.

---

[i] Market Guide for Customer Data Platforms, Gartner, March 2022

[ii] Hype Cycle for Digital Marketing, Gartner, July 2021

[iii] Customer Data Platform Industry Update, CDP Institute, January 2022

[iv] Ometria, https://ometria.com/blog/5-reasons-standalone-cdp-might-not-right-solution-retailers, January 2022

[v] What is RTIM, https://www.teradata.com/Glossary/What-is-RTIM, 2022

[vi] Forrester RTIM Wave, https://www.pega.com/forrester-rtim-2022, Q2 2022

Customer Analytics, Privacy, & Consent: 5 tips to turn bafflegab to genuine CX

How Next-Best-Action CX helps – before, during, & after a crisis

4 CX lessons – Use data & science to make better decisions

Shush – Listen for customer signals with event-based marketing & service

5 Hot AI in CX trends to watch in the roaring ‘20s

Customer analytics for CX: Protect, innovate, serve – OR PERISH

CRM strategy turns 25 – but has it helped CX?

The Hyper-Personalization Paradox: being relevant without crossing the CREEPY LINE