by Ebani Advertising | Aug 2, 2023 | Blog
Imagine a world where every advertisement you come across feels tailor-made just for you, resonating with your preferences, needs, and desires. This is the reality that AI-powered personalization is creating in the realm of advertising. In this blog post, we delve into the transformative impact of artificial intelligence on advertising campaigns and how it is reshaping the landscape through advanced personalization techniques.
Understanding the Power of AI-Powered Personalization
In the age of data, information is abundant. However, sifting through this vast sea of data to extract meaningful insights can be a daunting task. This is where AI steps in, with its unparalleled ability to analyse massive amounts of data swiftly and effectively. AI algorithms scrutinize consumer behaviour, preferences, and intent by examining various touchpoints – from browsing history and social media activity to purchase patterns and demographic information.
Unveiling Consumer Insights
The key to successful advertising lies in understanding your audience. AI empowers marketers with invaluable insights into consumer behaviours and trends. By recognizing patterns and correlations within data, AI can predict what products or services a consumer might be interested in. This knowledge is the foundation of creating highly targeted campaigns that resonate with individual needs.
Case Studies: AI in Action
Let’s explore a couple of case studies that highlight the game-changing potential of AI-driven insights in advertising:
1. Dynamic Content Generation
Incorporating AI-powered personalization into dynamic content generation allows advertisers to create multiple versions of an ad, each catering to a specific segment of their audience. For instance, a fashion retailer can showcase different clothing styles based on a user’s previous purchases or browsing history. This level of personalization significantly enhances the user experience, leading to higher engagement rates.
2. Recommendation Engines
Online platforms like Netflix and Amazon have mastered the art of recommendation engines. By analysing user behaviour, AI algorithms suggest content or products that align with the user’s preferences. This approach not only keeps users engaged but also drives sales by presenting them with options they are more likely to explore.
3. Predictive Analytics
Predictive analytics, fuelled by AI, enables advertisers to anticipate future consumer behaviours. By considering historical data and ongoing trends, advertisers can fine-tune their campaigns to align with what consumers are likely to desire next. This proactive approach ensures that ads remain relevant and compelling.
Integrating AI-Powered Personalization into Advertising Strategies
The seamless integration of AI-powered personalization into advertising strategies can yield remarkable results. Here are some tips for leveraging this technology effectively:
1. Crafting Compelling Ad Copy
AI can analyse user data to understand linguistic nuances that resonate with different segments of the audience. This insight helps in tailoring ad copy that speaks directly to users, capturing their attention and driving engagement.
2. Optimizing Ad Placements
AI can determine the most effective placement for an ad based on a user’s browsing habits. This ensures that ads appear where they are most likely to be noticed, increasing the chances of interaction.
3. A/B Testing with AI
A/B testing becomes even more potent when coupled with AI. Machine learning algorithms can quickly analyse test results and recommend adjustments to optimize campaign performance.
The Future of Advertising: Where AI Leads the Way
As we navigate the age of data, AI-powered personalization is undeniably a game-changer for the advertising industry. By delivering relevant and compelling content to consumers, AI enhances the user experience and boosts conversion rates. From understanding consumer behavior to predicting future trends, AI holds the key to unlocking new dimensions of advertising success.
FAQs About AI-Powered Advertising
Q1: Is AI-powered personalization suitable for all types of businesses?
Absolutely. Whether you’re a small e-commerce start-up or a multinational corporation, AI-powered personalization can be tailored to suit your business needs.
Q2: Does AI eliminate the need for human creativity in advertising?
Not at all. While AI assists in data analysis and insights, human creativity remains pivotal in designing engaging ad content.
Q3: How can I start implementing AI-powered personalization in my campaigns?
Begin by assessing your available data and exploring AI solutions that align with your goals. Collaborate with experts to ensure a seamless integration process.
Q4: Are there any ethical concerns regarding AI in advertising?
Ethical considerations, such as data privacy and algorithm transparency, are important. Striking a balance between personalization and privacy is crucial.
Q5: What skills do marketers need to leverage AI effectively?
Marketers need to understand the basics of AI and data analysis. Collaborating with data scientists and AI experts can further enhance AI utilization.
In conclusion, AI-powered personalization is ushering in a new era of advertising, where campaigns are no longer generic messages but personalized experiences. With the ability to dissect data and predict consumer behaviours, AI is at the forefront of revolutionizing advertising strategies. By integrating AI-driven insights into various aspects of marketing, businesses can create more meaningful connections with their audiences, ultimately driving engagement, conversions, and success.
by Ebani Advertising | Jul 15, 2023 | Blog
The Past
Traditionally, advertising agencies concentrated on crafting compelling advertisements, negotiating media contracts, and prioritizing client service. However, the advent of digital transformation disrupted this pattern, forcing agencies to rapidly adapt. In the wake of the digital era, businesses demanded more integrated and interactive strategies that transcended the one-way communication offered by traditional media. Ad agencies were compelled to transition into communication technology companies to stay relevant in this fast-paced digital evolution.
The Transformation
A communication technology company represents a natural evolution from a traditional advertising agency. The need for agencies to solely provide services in traditional advertising has dissipated with the surge in online platforms. The incorporation of technology and communication has become a necessity. Agencies now are expected to offer a full suite of digital services, such as website development, online advertising, social media management, and SEO.
Case Study: Real World Examples
R/GA
R/GA, based in New York, originated as a film production company in 1977. Recognizing the rising significance of technology in marketing, R/GA evolved into a prominent digital advertising agency known for its technology-driven marketing solutions. They offered services like interactive online ads, website development, and mobile apps.
One outstanding campaign by R/GA was with Nike for the creation of ‘Nike+ FuelBand,’ a wearable technology that allowed users to track their fitness activity. This innovative approach transformed the FuelBand into a medium for continuous consumer-brand interaction, significantly enhancing Nike’s brand visibility and engagement.
TBWA\Media Arts Lab
TBWA\Media Arts Lab, closely associated with Apple, is another agency that transitioned into a communication technology company. They expanded their offerings to include services like digital advertising, content marketing, social media strategy, and data analytics. Their ‘Shot on iPhone’ series, showcasing high-quality photos and videos taken by iPhone users worldwide, is a testament to their effective blend of technology and communication.
Wieden+Kennedy
Wieden+Kennedy, a traditional agency, adapted to the shifting media landscape by integrating technology into their campaigns. Their ‘Old Spice Man’ campaign started as a television commercial and later expanded to digital platforms, including YouTube and social media. This online campaign allowed the ‘Old Spice Man’ to interact with fans in real-time, attracting millions of views and boosting Old Spice’s brand image.
The Road Ahead: Challenges and Opportunities
The evolution from traditional advertising agencies to communication technology companies presents immense opportunities despite the challenges. The increasing demand for integrated, data-driven, and interactive communication strategies offers agencies the chance to deliver more effective, personalized, and holistic advertising solutions.
However, this transformation involves significant challenges such as constant upskilling, rapidly changing technologies, and managing data security and privacy issues.
Conclusion
In conclusion, the digital revolution has triggered a significant shift in the operations of advertising agencies. As they transition into communication technology companies, they leverage technology and data to create more meaningful, engaging, and personalized ad campaigns. The transformation has not only enabled them to stay competitive but has also positioned them as leaders in the rapidly evolving digital advertising landscape.
The transition requires more than just integrating technology; it also requires fostering a culture of learning, innovation, and agility. With the power of data and technology comes the responsibility of ethical considerations, including data handling, privacy, and security.
The future looks promising as advertising agencies continue to evolve, harnessing technology to deliver more impactful and personalized communication strategies, driving meaningful conversations and building stronger relationships between brands and their audiences in the digital era.
Part II: Transitioning From Traditional Media Practices to the Evolution of AI and the Way Forward
Transition from Traditional Media Practices
Traditional media practices had their core focus on television, radio, and print media – these were the primary mediums for advertising agencies to reach audiences. The advertising industry, during this era, was characterized by linear, one-way communication. Advertisers broadcasted their messages to consumers with little to no opportunity for engagement or interaction. However, the onset of the digital age and the proliferation of the internet and social media began to significantly alter the advertising landscape.
The Digital Transformation
The rise of digital platforms catalyzed a shift away from traditional media practices. Consumers began spending more time online, and advertisers saw an opportunity to reach these audiences through more targeted, personalized campaigns. Advertising agencies had to re-evaluate their strategies and business models to adapt to these changes.
Digital transformation pushed advertising agencies towards multichannel marketing, where they began creating advertisements for various platforms including websites, social media, and mobile apps. The transition wasn’t just about switching from one platform to another; it fundamentally altered how agencies approached advertising. Advertisers started focusing on interactive communication, enabling customers to participate and engage with the brands.
This period marked the beginning of agencies morphing into communication technology companies. Their roles were no longer limited to just creating ads, but also involved technology deployment, data analytics, and customer relationship management.
The Advent of AI
The emergence of Artificial Intelligence (AI) was another turning point in the evolution of advertising agencies. AI has revolutionized the advertising industry, providing tools for automation, personalization, and predictive analysis. It has enabled advertisers to gain insights into customer behavior, preferences, and purchasing habits like never before.
Agencies started using AI algorithms to predict future consumer behavior based on historical data. They could anticipate consumer responses to different marketing strategies and tailor their campaigns accordingly. AI also automated repetitive tasks such as ad buying and placement, saving agencies time and resources.
The integration of AI within their operations marked another milestone in the transition of advertising agencies into communication technology companies. Now, they could not only create and distribute ads across multiple platforms but also use AI to optimize their campaigns and achieve better results.
The Way Forward: Embracing AI and Future Technologies
Looking ahead, the future of advertising agencies as communication technology companies seems to be intertwined with the future of AI and emerging technologies. With advancements in AI capabilities, agencies are expected to take personalization to a whole new level. For instance, using AI algorithms, they can create personalized ads tailored to each individual based on their preferences, online behavior, and purchasing history.
Furthermore, technologies like Augmented Reality (AR) and Virtual Reality (VR) are opening new avenues for interactive advertising. Agencies can leverage these technologies to create immersive ad experiences, bringing products to life and allowing consumers to interact with them virtually.
Another significant development is the growing importance of data privacy and ethics. As agencies collect and process large amounts of personal data, they must ensure they are respecting users’ privacy and adhering to data protection regulations. This will be a crucial aspect of their operations in the future.
Conclusion
In conclusion, the journey of advertising agencies from traditional media practices to communication technology companies is a story of continuous adaptation and evolution. It’s a tale of embracing new technologies and trends while maintaining a steadfast commitment to delivering value to clients. As agencies look forward to a future powered by AI and emerging technologies, they need to stay agile and innovative, continuously learning and adapting to stay ahead in this fast-paced industry.
The evolution of advertising agencies into communication technology companies is not just about integrating technology into their operations. It’s about fostering a culture that embraces change, values learning, and prioritizes innovation. As they continue this journey, they have the opportunity.
by Ebani Advertising | Jul 1, 2023 | Blog
All images in this article were created using generative AI. These images were created using the prompts light bulb, flower, pastel, geometric shapes, simplicity, clean lines, and minimal still life. Midjourney
Summary: There is tremendous apprehension about the potential of generative AI—technologies that can create new content such as text, images, and video—to replace people in many jobs. But one of the biggest opportunities generative AI offers is to augment human creativity and overcome the challenges of democratizing innovation.
In the past two decades, companies have used crowdsourcing and idea competitions to involve outsiders in the innovation process. But many businesses have struggled to capitalize on these contributions. They’ve lacked an efficient way to evaluate the ideas, for instance, or to synthesize different ideas.
Generative AI can help overcome those challenges, the authors say. It can supplement the creativity of employees and customers and help them produce and identify novel ideas—and improve the quality of raw ideas. Specifically, companies can use generative AI to promote divergent thinking, challenge expertise bias, assist in idea evaluation, support idea refinement, and facilitate collaboration among users.
The term “democratizing innovation” was coined by MIT’s Eric von Hippel, who, since the mid-1970s, has been researching and writing about the potential for users of products and services to develop what they need themselves rather than simply relying on companies to do so. In the past two decades or so, the notion of deeply involving users in the innovation process has taken off, and today companies use crowdsourcing and innovation contests to generate a multitude of new ideas. However, many enterprises struggle to capitalize on these contributions because of four challenges.
First, efforts to democratize innovation may result in evaluation overload. Crowdsourcing, for instance, may produce a flood of ideas, many of which end up being dumped or disregarded because companies have no efficient way to evaluate them or merge incomplete or minor ideas that could prove potent in combination.
Second, companies may fall prey to the curse of expertise. Domain experts who are best at generating and identifying feasible ideas often struggle with generating or even accepting novel ideas.
Third, people who lack domain expertise may identify novel ideas but may be unable to provide the details that would make the ideas feasible. They can’t translate messy ideas into coherent designs.
And finally, companies have trouble seeing the forest for the trees. Organizations focus on synthesizing a host of customer requirements but struggle to produce a comprehensive solution that will appeal to the community at large.
Generative AI tools can solve an important challenge faced in idea contests: combining or merging a large number of ideas to produce much stronger ones.
Our research and our experience working with companies, academic institutions, governments, and militaries on hundreds of innovation efforts—some with and some without the use of generative AI—have demonstrated that this technology can help organizations overcome these challenges. It can augment the creativity of employees and customers and help them generate and identify novel ideas—and improve the quality of raw ideas. We have observed the following five ways.
1. Promote Divergent Thinking
Generative AI can support divergent thinking by making associations among remote concepts and producing ideas drawn from them. Here’s an example of how we used Midjourney, a text-to-image algorithm that can detect analogical resemblances between images, to generate novel product designs based on textual prompts from a human. (We utilized Midjourney, ChatGPT, and Stable Diffusion for the examples in this article, but they are just a few of a host of generative AI tools that are now available.) We asked Midjourney to create an image that combined an elephant and a butterfly, and it produced the chimera we dubbed “phantafly.”
We then used the detailed rendering from Midjourney to inspire prompts in Stable Diffusion, another popular text-to-image model. Stable Diffusion generated a range of ideas for different product categories, including chairs and artisanal chocolate candies (see images below).
The authors prompted Midjourney to produce an image combining an elephant and a butterfly; they dubbed this creation “phantafly” (left). Then the authors prompted Stable Diffusion to generate designs for chairs and for artisanal chocolates inspired by “phantafly” (right). Midjourney; Stable Diffusion
Rapidly and inexpensively producing a plethora of designs in this way allows a company to evaluate a wide range of product concepts quickly. For example, a clothing company that uses generative AI to create new designs for T-shirts could stay on top of trends and offer a constantly changing selection of products to customers.
Consider another example of how this technology can connect ideas to create concepts that an individual or a team might never have come up with themselves. We used ChatGPT, a type of generative AI known as a large language model, to guide the production of ideas. We asked it to generate ideas through a process of trisociation by connecting three distinct entities (an extension of the bisociation creativity technique). Our team gave ChatGPT the following prompt: “You will play the role of an ideator. You will randomly generate 10 common nouns. You will then randomly select any two of the 10 nouns. You will then ask me for a third noun. You will generate a business idea by combining or associating the two nouns you identified and the noun I identified.”
ChatGPT generated the nouns “food” and “technology.” When prompted, we provided the additional noun “car.” ChatGPT produced the following business idea in short order: “A smart food-delivery service that uses self-driving cars to transport meals to customers. The technology aspect could involve using AI to optimize delivery routes, track food temperature in real time, and provide customers with real-time updates on the status of their orders. The service could target busy professionals and families who want convenient and healthy meal options without sacrificing taste and quality.”
In a separate round, ChatGPT produced the nouns “airline” and “chair.” When prompted, we provided “university,” and ChatGPT came up with a business concept that provides a convenient, cost-effective way for students and academics to travel to conferences and workshops around the world along with access to a library of educational books during the flight. It proposed that the company be called Fly and Study or Edu-Fly.
2. Challenge Expertise Bias
During the early stages of new-product development, atypical designs created by generative AI can inspire designers to think beyond their preconceptions of what is possible or desirable in a product in terms of both form and function. This approach can lead to solutions that humans might never have imagined using a traditional approach, where the functions are determined first and the form is then designed to accommodate them. These inputs can help overcome biases such as design fixation (an overreliance on standard design forms), functional fixedness (a lack of ability to imagine a use beyond the traditional one), and the Einstellung effect, where individuals’ previous experiences impede them from considering new ways to solve problems.
Here’s an example of this process. We asked Stable Diffusion to generate generic designs of crab-inspired toys but provided it with no functional specifications. Then we imagined functional capabilities after seeing the designs. For instance, in the collection of crab-inspired toys shown below, the image in the top left could be developed into a wall-climbing toy; the image next to it could be a toy that launches a small ball across a room. The crab on a plate near the center could become a slow-feeder dish for pets.
The authors asked Stable Diffusion to come up with crab-inspired toy concepts. Stable Diffusion
This is not a completely novel way to come up with unusual products: Much of the architecture and ride functionality in theme parks such as Disney World has been driven by a desire to re-create scenes and characters from a story. But generative AI tools can help jump-start a company’s imaginative designs.
3. Assist in Idea Evaluation
Generative AI tools can assist in other aspects of the front end of innovation, including by increasing the specificity of ideas and by evaluating ideas and sometimes combining them. Consider an innovation challenge where the goal is to identify ways to minimize food waste. ChatGPT assessed the pros and cons of three raw ideas: (1) packaging with dynamic expiration dates (labels that automatically change either the dates or colors based on the environmental conditions in the places where they are stored); (2) an app to help users donate food; and (3) a campaign to educate people on types of expiration dates and what they represent in terms of freshness and fitness for use. ChatGPT produced a balanced analysis of the pros and cons that mirrored what we might expect from an exchange between two interested persons discussing the merits of such ideas.
When ChatGPT evaluated the concept of dynamic expiration-date packaging, for instance, it determined that it would help consumers better understand the shelf life of products and encourage food manufacturers to produce smaller batches that would be replenished more frequently on grocery shelves. In addition, ChatGPT pointed out that dynamic expiration dates may require significant changes to the manufacturing and packaging process and as a result, could increase the costs to both manufacturers and consumers.
ChatGPT determined that the food-donation app could encourage people to use up their food before it goes bad and reduce food waste by giving unopened, edible food to those in need. It cautioned that the app may require a large user base to be effective and that the transportation and distribution of food from a wide variety of unregulated sources could pose safety concerns.
Generative AI’s greatest potential is not replacing humans; it is to assist humans in their efforts to create hitherto unimaginable solutions.
It stated that the pros of an education program for consumers were increasing consumer awareness of the meaning of different expiration labels and helping them make more-informed decisions about food purchases and waste. But ChatGPT warned that this education program could be overly complex because expiration dates are not standardized across all food products. And it cautioned that educating users on different types of expiration dates can be costly if the program is broad in scope, particularly if it involves widespread campaigns or educational materials.
Generative AI can go beyond simple pros and cons and help humans evaluate dimensions of creativity such as novelty, feasibility, specificity, impact, and workability. We asked ChatGPT to assess the same examples using these criteria.
Here is its assessment of the dynamic expiration-date packaging concept:
Novelty: Somewhat novel. There have been efforts to develop smart packaging that can extend the shelf life of food products, but the idea of dynamic expiration dates is an emerging concept.
Feasibility: May be challenging to implement as it requires the development of new packaging materials and technologies. It would also require collaboration with food manufacturers, regulators, and distributors.
Specificity: It’s specific in that it addresses the problem of food waste by providing consumers with more-accurate expiration dates for their food.
Impact: Could have a significant impact on reducing food waste and improving food safety. When provided with more-accurate expiration dates, consumers would be more likely to use their food before it goes bad.
Workability: It would most likely require significant resources and expertise to develop and implement and may take several years to fully realize its potential.
Here is ChatGPT’s assessment of the app for donating food close to expiration:
Novelty: Not particularly novel. There are already many programs and organizations dedicated to reducing food waste and donating surplus food to those in need.
Feasibility: Highly feasible. There are many established models and an infrastructure in place to support food donation efforts.
Specificity: Specific in its aim to reduce food waste and address issues of food insecurity.
Impact: Has the potential to make a significant impact as it addresses both food waste and hunger. By redirecting surplus food to those in need, it can help reduce food waste while also improving food security for vulnerable populations.
Workability: Highly workable in that it can be implemented quickly and at a relatively low cost. It would require partnerships with food manufacturers, distributors, and food banks, as well as volunteers to collect and distribute the donated food.
Finally, here is how ChatGPT evaluated the idea to educate users on different types of expiration dates:
Novelty: Not particularly novel. There have been efforts to educate consumers on the meaning of expiration dates and how to properly store food to extend its shelf life.
Feasibility: Highly feasible. It can be implemented through various means, such as public awareness campaigns, educational materials, and media outreach.
Specificity: Specific in its aim to educate consumers on the different expiration dates and how to properly store food to reduce food waste.
Impact: Potentially significant. Educating consumers on the different expiration dates and how to properly store food will make them more mindful of food waste and take steps to reduce it.
Workability: Highly workable and can be implemented at a relatively low cost. It would require collaboration with food industry groups, government agencies, and other organizations to develop and distribute educational materials.
Using ChatGPT’s assessments, it would be relatively easy to evaluate these three concepts, or quickly score or organize them based on the criteria that matter most.
4. Support Idea Refinement
Generative AI tools can solve an important challenge faced in idea contests: combining or merging a large number of ideas to produce much stronger ones. For example, an organization that is trying to win a contract or a grant to develop a food-waste-reduction program can use the tools to combine the three concepts discussed earlier. We did this in two steps. First, we asked ChatGPT to flesh out each of the concepts:
- “Dynamic expiration dates are a solution aimed at reducing food waste. This involves incorporating technology into packaging that can track and adjust the shelf life of products in real time. By using sensors, the expiration date can be updated based on changes in environmental factors, providing consumers with a more accurate estimate of when a product will go bad.”
- “An app that enables consumers to donate food close to its expiration date aims to reduce food waste by giving unopened, edible food to those in need. The app connects individuals who have surplus food to local organizations that can use it. By using technology to facilitate food donations, the app can help reduce food waste and provide for those in need.”
- “Educating users on the different types of expiration dates can help users make informed decisions about purchasing and consuming food, reducing waste, and saving money. By clarifying the meaning of ‘best before,’ ‘use by,’ and other expiration labels, an education campaign can help users better understand how to determine if food is safe to eat and when it is time to dispose of it.”
Next we asked ChatGPT to merge all three ideas into one food-waste program. In short order it produced the following description: “The comprehensive food-waste-reduction solution involves creating smart packaging with dynamic expiration dates, establishing a program for donating surplus food, and educating the public on the importance of understanding food expiration dates. The smart packaging helps consumers make informed decisions about food freshness, the donation program ensures surplus food is put to good use, and education raises awareness about the impact of food waste. This solution has the potential to significantly reduce food waste and create a more sustainable future by empowering consumers, working with industry and government, and making better use of surplus food.”
5. Facilitate Collaboration with and Among Users
When developing new product ideas or designs, generative AI can facilitate collaborations between a company’s designers and users of a prospective product and among users themselves. In other words, the technology makes co-creation of new offerings much easier and less expensive. For example, a business can give users access to tools to generate designs and then create a personalized version of the product based on the customer’s preferences. Alternatively, users’ designs could be posted on a crowdsourcing platform where they are evaluated by the community. The top designs could then be further developed by additional collaborators.
To illustrate the potential, we show how a flying car—something people have been trying to develop for more than 100 years without much success—might be designed. We gave Stable Diffusion this prompt: “Design a product that can fly but also drive on the road, a flying automobile.” Stable Diffusion generated several designs, and we selected what we considered to be the most promising one: the vehicle in the lower right corner of the image below.
The authors asked Stable Diffusion to design a flying automobile. Stable Diffusion
Then we asked Stable Diffusion to take that design and reimagine the concept so that the car “resembles a robot eagle.” The image below shows the variations that the generative AI program quickly produced—from the top left design that looks most like a robot eagle to the more feasible concept of a flying automobile in the lower right corner.
The authors chose one of the flying-automobile designs and asked Stable Diffusion to reimagine it to resemble a robot eagle. Stable Diffusion
A second example illustrates how designers can use such tools to collaborate on thematic variations of a structural design. They began with a flying-automobile design generated by AI and asked the tool to produce versions that resembled a dragonfly, a tiger, a tortoise, and an eagle (see image below).
This image is another AI-generated concept of a flying car (left) with versions that resemble a dragonfly, a tiger, a tortoise, and an eagle (right). Stable Diffusion
An alternate approach is for human collaborators to use a tool like ChatGPT to develop details of the product and then use one like Stable Diffusion to obtain visual designs based on a series of prompts that build upon one another. We gave ChatGPT a similar prompt to what we had given to Stable Diffusion: “Describe a product that can fly but also drive on the road, a flying automobile.”
ChatGPT provided this description: “The flying automobile is a sleek and futuristic vehicle that is built for the ultimate adventure. It has the appearance of a stylish sports car with smooth curves and polished exterior but with hidden rotors that allow it to take flight.”
When we gave that description to Stable Diffusion, it provided the image below on the left. Next we asked ChatGPT to reimagine the description to include the information that the product must resemble a dragonfly and have illumination markers for flying at night. It came back with the following: “With its slender body, extended wings, and hidden rotors, the vehicle is reminiscent of a dragonfly come to life. The illuminated markers located along the wings and body create a stunning visual effect, helping to make the vehicle visible in the darkness.”
Stable Diffusion translated that description into various versions that maintained the feasible design and added elements of illumination based on the pattern of a dragonfly’s wings. The images below on the right are examples.
The authors used ChatGPT to describe a flying automobile and asked Stable Diffusion to generate a design from that description (left) and then variations on the design that incorporate dragonfly details and illumination (right). Stable Diffusion
Humans have boundless creativity. However, the challenge of communicating their concepts in written or visual form restricts vast numbers of people from contributing new ideas. Generative AI can remove this obstacle. As with any truly innovative capability, there will undoubtedly be resistance to it. Long-standing innovation processes will have to change. People with vested interests in the old way of doing things—especially those worried about being rendered obsolete—will resist. But the advantages—the opportunities to dramatically increase the number and novelty of ideas from both inside and outside the organization—will make the journey worthwhile. Generative AI’s greatest potential is not replacing humans; it is to assist humans in their individual and collective efforts to create hitherto unimaginable solutions. It can truly democratize innovation.
Use it to promote divergent thinking. by Tojin T. Eapen, Daniel J. Finkenstadt, Josh Folk, and Lokesh Venkataswamy
by Ebani Advertising | Jun 26, 2023 | Blog
Summary: Authenticity is among Gen Z’s most important values. They feel empowered to ask and answer their own questions in a variety of social forums on any topic — from beauty to health to home improvement to technology to science. And their view of authority has expanded from traditional sources, like academic institutions or reputable editorial voices, to perceived influence. The author offers five lessons for brands who want to tap into this era of influencers and make authentic connections with Gen Z
If you haven’t heard about Alix Earle, it may simply be a matter of time. This young influencer — who just graduated from the University of Miami — has more than 5 million followers on TikTok and was recently signed by United Talent Agency (UTA), one of the top three firms that represent talent globally across the media and entertainment ecosystem. She has leveraged her personal brand to partner with beauty companies like Tarte and Rare Beauty.
Watching the myriad of Alix Earle videos online makes her formula quite clear. She has model-like beauty, checking the box for sheer aesthetics. She’s perfected the “get ready with me” (GRWM) format (among others), a short-form video in which she goes from natural beauty to flawless perfection, displaying professional yet replicable makeup techniques and product use. As she applies her look during “selfie” videos, she offers a mix of storytelling, humor, vulnerability, aspiration, relatability, and product mentions in a fast-talking, effortless monologue. She feels just approachable enough to be just another college student.
That approachability is why Earle resonates so much with Gen Z. Authenticity is among this generation’s most important values. As recent EY research highlights: “After an era of fake news and filtered photos projecting the ‘perfect life,’ Gen Z is over it.” They feel empowered to ask and answer their own questions in a variety of social forums on any topic — from beauty to health to home improvement to technology to science. And their view of authority has expanded from traditional sources, like academic institutions or reputable editorial voices, to perceived influence — as demonstrated by Earle’s meteoric rise.
Studying Alix Earle’s success offers brand marketers five powerful lessons for how to tap into this era of influencers — and make authentic connections with Gen Z.
1. Find the right influencers for your brand
Simply force-ranking top influencer lists is not the answer. Brands want to find the person or people who reach their target audience.
Once brands define the category in which they compete, marketers can look for the influencers who have the most engagement and who have a voice and style that resonates with the brand. AI and other tools to analyze data can help you figure this out — for example, data analytics can reveal followers, creative approaches, and communities in common between influencers and brands. There are also companies, from Gallery Media, for example, to leading talent agencies, who curate influencers and manage more complex relationships and execution for brands.
2. Create brand stories for mobile consumption
Gen Z fills their spare moments by scrolling through their algorithmically driven, personalized “for you” feeds on their phones, filled with photos, videos, and memes. Ideally, brands should empower the influencers they work with to create content that is short, compelling, and made for mobile.
Embracing vulnerability and openness, like Earle does in short one- to three-minute stories, enables brands to connect with younger generations in a way that’s personally relevant and authentic. However, brands must understand that this is not a 30-second scripted television spot, and the influencers will take the story in a direction of their own choosing. This is a complement to other brand storytelling — not a replacement.
3. Motivate consumers to make brand content their own
Unlike previous generations, Gen Z does not “broadcast” their posts to social networks writ large. They share more often with far fewer people via “private stories.” Engagement is much higher because of the frequency and the intimacy of these posts, and with this shift, we also see Gen Z moving away from prior generational behaviors of broadcasting their happy moments widely on their social media accounts to sharing more raw moments like personal crisis and tears in more private circles.
A young person who sees a beauty product in a GRWM video from Earle on TikTok who subsequently endorses that product with their friend group in their private story on Snap is an example of how the brand journey goes from high-profile social media influence to deeply personal influence. A brand must earn the right to access this sacred space — and it must understand the opacity and new risks of these more personally intimate venues.
4. Cross boundaries to stand out
It’s going to take new sources of inspiration and creativity to stand out as generative and conversational AI are applied in creative contexts at scale. As all influencers now have access to the same technology to drive research, enhance ideas, and accelerate production, forward-thinking brands will look to differentiate through human originality or true celebrity. The bar for real creativity will only get higher, requiring unorthodox juxtapositions of brands or new invitations to consumers to co-create. Our current definition of influence may shift rapidly as AI manipulates both the targeting and creative driving the algorithms.
5. Avoid clone culture
As marketers, we may prize the opportunity to drive consumption at all costs by engineering trends to have velocity through influencers. But if we succeed too much on the science of it all, are we creating trend echo chambers that contradict our commitments to diversity and inclusion, or cloning repeat behaviors within certain social archetypes? And if influence relies on at least the veneer of originality, will it be harder as everyone uses similar AI-driven insights? Brands drive their commercial ambition with precision using a combination of creativity and data (or art and science), but increasingly, they may seek to broaden strategies to find new audiences, voices, and inspiration to diversify their base of consumers and ideas.
The creator economy is thriving, creative, and valuable, particularly as technology-enabled economic models motivate strong talent to make it a true professional endeavor. Brands that harness its new dynamics to create value will differentiate themselves and drive exponential growth. The key to success is to lean into the newest sources of influence along with all the latest dynamics of risk and reward.
The views reflected in this article are the views of the author and do not necessarily reflect the views of Ernst & Young LLP or other members of the global EY organization.
Credit: Janet Balis
by Ebani Advertising | Jun 5, 2023 | Blog
Summary: The recent advances in ChatGPT are merely the first application of new AI technologies. As such, companies and leaders need to think about the various applications outlined here and use the framework described in the article to develop applications for your own company or organization. In the process, they will discover new types of GPTs. By classifying these different GPTs in terms of potential value to businesses and the cost of developing them, applications that begin with a single human initiating or participating in the interaction (GroupGPT, CoachGPT) will probably be the easiest to build and should generate substantial business value, making them the perfect initial candidates. In contrast, applications with interactions involving multiple entities or those initiated by machines (AutoGPT, BossGPT, and ImperialGPT) may be harder to implement, with trickier ethical and legal implications.
The frenzy surrounding the launch of Large Language Models (LLMs) and other types of Generative AI (GenAI) isn’t going to fade anytime soon. Users of GenAI are discovering and recommending new and interesting use cases for their business and personal lives. Many recommendations start with the assumption that GenAI requires a human prompt. Indeed, Time magazine recently proclaimed “prompt engineering” to be the next hot job, with salaries reaching $335,000. Tech forums and educational websites are focusing on prompt engineering, with Udemy already offering a course on the topic, and several organizations we work with are now beginning to invest considerable resources in training employees on how best to use ChatGPT.
However, it may be worth pausing to consider other ways of interacting with GPT technologies, which are likely to emerge soon. We present an intuitive way to think about this issue, which is based on our own survey of GenAI developments, combined with conversations with companies that are seeking to develop some versions of these.
A Framework of GPT Interactions
A good starting point is to distinguish between who is involved in the interaction — individuals, groups of people, or another machine — and who starts the interaction, human or machine. This leads to six different types of GenAI uses, shown below. ChatGPT, where one human initiates interaction with the machine is already well-known. We now describe each of the other GPTs and outline their potential.
CoachGPT is a personal assistant that provides you with a set of suggestions on managing your daily life. It would base these suggestions not on explicit prompts from you, but on the basis of observing what you do and your environment. For example, it could observe you as an executive and note that you find it hard to build trust in your team; it could then recommend precise actions to overcome this blind spot. It could also come up with personalized advice on development options or even salary negotiations.
CoachGPT would subsequently see which recommendations you adopted or didn’t adopt, and which benefited you and which ones didn’t to improve its advice over time. With time, you would get a highly personalized AI advisor, coach, or consultant.
Organizations could adopt CoachGPT to advise customers on how to use a product, whether a construction company offering CoachGPT to advise end users on how best to use its equipment, or an accounting firm proffering real-time advice on how best to account for a set of transactions.
To make CoachGPT effective, individuals and organizations would have to allow it to work in the background, monitoring online and offline activities. Clearly, serious privacy considerations need to be addressed before we entrust our innermost thoughts to the system. However, the potential for positive outcomes in both private and professional lives is immense.
GroupGPT would be a bona fide group member that can observe interactions between group members and contribute to the discussion. For example, it could conduct fact checking, supply a summary of the conversation, suggest what to discuss next, play the role of devil’s advocate, provide a competitor perspective, stress-test the ideas, or even propose a creative solution to the problem at hand.
The requests could come from individual group members or from the team’s boss, who need not participate in team interactions, but merely seeks to manage, motivate, and evaluate group members. The contribution could be delivered to the whole group or to specific individuals, with adjustments for that person’s role, skill, or personality.
The privacy concerns mentioned above also apply to GroupGPT, but, if addressed, organizations could take advantage of GroupGPT by using it for project management, especially on long and complicated projects involving relatively large teams across different departments or regions. Since GroupGPT would overcome human limitations on information storage and processing capacity, it would be ideal for supporting complex and dispersed teams.
BossGPT takes an active role in advising a group of people on what they could or should do, without being prompted. It could provide individual recommendations to group members, but its real value emerges when it begins to coordinate the work of group members, telling them as a group who should do what to maximize team output. BossGPT could also step in to offer individual coaching and further recommendations as the project and team dynamics evolve.
The algorithms necessary for BossGPT to work would be much more complicated as they would have to consider somewhat unpredictable individual and group reactions to instructions from a machine, but it could have a wide range of uses. For example: an executive changing job could request a copy of her reactions to her first organization’s BossGPT instructions, which could then be used to assess how she would fit into the new organization — and the new organization-specific BossGPT.
At the organizational level companies could deploy BossGPT to manage people, thereby augmenting — or potentially even replacing — existing managers. Similarly, BossGPT has tremendous applications in coordinating work across organizations and managing complex supply chains or multiple suppliers.
Companies could turn BossGPT into a product, offering their customers AI solutions to help them manage their business. These solutions could be natural extensions of the CoachGPT examples described earlier. For example, a company selling construction equipment could offer BossGPT to coordinate many end users on a construction site, and an accounting firm could provide it to coordinate the work of many employees of its customers to run the accounting function in the most efficient way.
AutoGPT entails a human giving a request or prompt to one machine, which in turn engages other machines to complete the task. In its simplest form, a human might instruct a machine to complete a task, but the machine realizes that it lacks a specific software to execute it, so it would search for the missing software on Google before downloading and installing it, and then using it to finish the request.
In a more complicated version, humans could give AutoGPT a goal (such as creating the best viral YouTube video) and instruct it to interact with another GenAI to iteratively come up with the best ChatGPT prompt to achieve the goal. The machine would then launch the process by proposing a prompt to another machine, then evaluate the outcome, and adjust the prompt to get closer and closer to the final goal.
In the most complicated version, AutoGPT could draw on functionalities of the other GPTs described above. For example, a team leader could task a machine with maximizing both the effectiveness and job satisfaction of her team members. AutoGPT could then switch between coaching individuals through CoachGPT, providing them with suggestions for smoother team interactions through GroupGPT, while at the same time issuing specific instructions on what needs to be done through BossGPT. AutoGPT could subsequently collect feedback from each activity and adjust all the other activities to reach the given goal.
Unlike the above versions, which are still to be created, a version of AutoGPT has been developed and was rolled out in April 2023, and it’s quickly gaining broad acceptance. The technology is still not perfect and requires improvements, but it is already evident that AutoGPT is able to complete a set of jobs that requires the completion of several tasks one after the other.
We see its biggest applications in complex tasks, such as supply chain coordination, but also in fields such as cybersecurity. For example, organizations could prompt AutoGPT to continually address any cybersecurity vulnerabilities, which would entail looking for them — which already happens — but then instead of simply flagging them, AutoGPT would search for solutions to the threats or write its own patches to counter them. A human might still be in the loop, but since the system is self-generative within these limits, we believe that AutoGPT’s response is likely to be faster and more efficient.
ImperialGPT is the most abstract GenAI — and perhaps the most transformational — in which two or more machines would interact with each other, direct each other, and ultimately direct humans to engage in a course of action. This type of GPT worries most AI analysts, who fear losing control of AI and AI “going rogue.” We concur with these concerns, particularly if — as now — there are no strict guardrails on what AI is allowed to do.
At the same time, if ImperialGPT is allowed to come up with ideas and share them with humans, but its ability to act on the ideas is restricted, we believe that this could generate extremely interesting creative solutions especially for “unknown unknowns,” where human knowledge and creativity fall short. They could then easily envision and game out multiple black swan events and worst-case scenarios, complete with potential costs and outcomes, to provide possible solutions.
Given the potential dangers of ImperialGPT, and the need for tight regulation, we believe that ImperialGPT will be slow to take off, at least commercially. We do anticipate, however, that governments, intelligence services, and the military will be interested in deploying ImperialGPT under strictly controlled conditions.
Implications for your Business
So, what does our framework mean for companies and organizations around the world? First and foremost, we encourage you to step back and see the recent advances in ChatGPT as merely the first application of new AI technologies. Second, we urge you to think about the various applications outlined here and use our framework to develop applications for your own company or organization. In the process, we are sure you will discover new types of GPTs that we have not mentioned. Third, we suggest you classify these different GPTs in terms of potential value to your business, and the cost of developing them.
We believe that applications that begin with a single human initiating or participating in the interaction (GroupGPT, CoachGPT) will probably be the easiest to build and should generate substantial business value, making them the perfect initial candidates. In contrast, applications with interactions involving multiple entities or those initiated by machines (AutoGPT, BossGPT, and ImperialGPT) may be harder to implement, with trickier ethical and legal implications.
You might also want to start thinking about the complex ethical, legal, and regulatory concerns that will arise with each GPT type. Failure to do so exposes you and your company to both legal liabilities and — perhaps more importantly — an unintended negative effect on humanity.
Our next set of recommendations depends on your company type. A tech company or startup, or one that has ample resources to invest in these technologies, should start working on developing one or more of the GPTs discussed above. This is clearly a high-risk, high-reward strategy.
In contrast, if your competitive strength is not in GenAI or if you lack resources, you might be better off adopting a “wait and see” approach. This means you will be slow to adopt the current technology, but you will not waste valuable resources on what may turn out to be only an interim version of a product. Instead, you can begin preparing your internal systems to better capture and store data as well as readying your organization to embrace these new GPTs, in terms of both work processes and culture.
The launch and rapid adoption of GenAIs is rightly being considered as the next level in the evolution of AI and a potentially epochal moment for humanity in general. Although GenAIs represent breakthroughs in solving fundamental engineering and computer science problems, they do not automatically guarantee value creation for all organizations. Rather, smart companies will need to invest in modifying and adapting the core technology before figuring out the best way to monetize the innovations. Firms that do this right may indeed strike it rich in the GenAI goldrush.
Credit: by Misiek Piskorski and Amit Joshi
by Ebani Advertising | May 31, 2023 | Blog
Startups: loved or hated, they remain a driving force of innovation and growth. These dynamic organizations offer abundant opportunities for career advancement, creativity, and personal fulfillment. However, working in a startup can also be highly demanding and stressful, with tight deadlines, limited resources, and constant change.
This intense environment can lead to burnout and mental health issues. Gallup’s 2022 State of the Global Workplace report revealed that 44% of US employees experienced high daily stress. Working women in the US and Canada were among the most stressed globally. Chronic work stress is linked to anxiety, depression, and physical health problems. So how can we survive and prevent burnout in fast-paced jobs?
The Consequences of Fast-Paced Environments: Burnout To navigate the challenges and build resilience in a startup environment, employees must develop effective coping strategies. Joseph Yeh, who has over 20 years of experience in recruiting and consulting for startups, including working with former Yahoo CEO Marissa Mayer, acknowledges the importance of self-care. “At the end of the day, you need to take care of yourself,” he says.
Developing resilience requires self-honesty and transparent communication with your team. Practical habits and tools for managing workflow also contribute to sustaining resilience. But success in a fast-paced startup goes beyond basic time management strategies. It involves understanding the unique dynamics of startup culture and how your personality aligns with your employer. Only then can your strategies support long-term resilience.
Why Startups are Fast-Paced Startups are notorious for their long hours and intense work culture. John Ferneborg, a recruiter for tech startups, explains that startups are still searching for product fit. The competition is fierce, and companies need to get their most competitive product to market quickly. As circumstances change rapidly, sharing expectations and building resilience through constant communication is crucial.
Fueling Motivation Between You and Your Employer While work-life balance and flexible schedules are gaining emphasis, they may seem contradictory to the traditional startup ethos. Not everyone fits the fast-paced work environment, and failing to align with the startup’s culture and values can lead to burnout.
Passion and perseverance are key drivers for success in fast-paced startup environments. Yeh and Ferneborg stress the importance of knowledge, learning, and working with passionate people. Understanding and communicating your motivations and passions promote a supportive work environment that aligns with personal and professional growth.
Key Habits and Tools to Thrive in a Fast-Paced Work Environment Open communication with your employer, manager, and coworkers is essential for building and maintaining resilience in organized chaos. This involves being honest with yourself and your team and adopting habits and tools to manage your workflow.
Self-awareness for Mutual Understanding Self-awareness means understanding your workplace preferences, receiving feedback, building relationships, communication style, and metrics for success. Communicating these details to your team is essential for effective collaboration.
Create a Self-Awareness Checklist Document the best ways to work with you and share it with new managers and colleagues. Highlight your preferred methods of communication and work style, fostering mutual understanding.
Honesty about Your Schedule Define your schedule early on to avoid taking on excessive work and burning out. Be transparent about your workload, set boundaries, and communicate your availability and non-negotiable personal commitments.
Create a Schedule That Works for You Establish a schedule that suits your preferences, considering when you’re most productive. Communicate your schedule to your team, allowing for focused work and personal time.
Understanding the Company’s Workflow Comprehend the company’s workflow, including schedules, reports, and meetings, and align your own schedule accordingly. Communicate changes in advance to adjust your schedule effectively.
Additional Tips for Building Resil ience Build strong relationships with your manager and coworkers by fostering open and transparent communication. Understanding the context of your communication with them will help you translate your needs into support, further enhancing your resilience.
Finding mentors can be immensely helpful. Seek out different types of mentors, such as peer mentors, devil’s advocate mentors, god-parent mentors, and career coach mentors. They can provide guidance, challenge your perspectives, open doors for you, and offer personal and professional support.
Consider getting a work phone to cut out distractions. By having a separate phone for work-related messages, you can better focus when needed and disconnect when required, promoting a healthier work-life balance.
Learn to say no strategically. It’s important to communicate your schedule and work style with your manager and coworkers, so they understand your boundaries and limitations. When you say no, they will already be aware of the reasons behind it and should respect your decision.
Don’t give up right away. It can be challenging to find the right fit in a fast-paced startup environment. If you’re new to the industry or haven’t found the ideal workplace yet, try to stick it out for at least six months or a year. Use this time to learn about your work style, identify what schedule works best for you, and build strong communication channels with your manager and colleagues. Expressing your needs and seeking support will help you develop the resilience necessary for any job.
In conclusion, surviving and thriving in a fast-paced startup environment requires developing resilience and implementing effective strategies. By practicing self-awareness, open communication, and strategic time management, you can navigate the challenges, prevent burnout, and achieve long-term success. Remember, taking care of yourself is crucial, and building strong relationships and seeking mentorship can provide invaluable support along the way. With the right habits, tools, and mindset, you can not only survive but also thrive in the startup jungle.
