Generative AI: How Business-Changing Solutions Like ChatGPT Could Be Used

75
Credit: Hitesh Choudhary/Unsplash

The game of artificial intelligence is evolving thanks to generative AI and other foundation models, which are also speeding up application development and giving non-technical people access to significant capabilities, as reported by McKinsey.

ChatGPT

In the spirit of this article’s topic, we asked ChatGPT—a generative AI language model that can create original content in response to a user prompt—how it would set the context. Our prompt to the system:

ChatGPT’s response:

The rise of generative AI has the potential to be a major game-changer for businesses. This technology, which allows for the creation of original content by learning from existing data, has the power to revolutionize industries and transform the way companies operate. By enabling the automation of many tasks that were previously done by humans, generative AI has the potential to increase efficiency and productivity, reduce costs, and open up new opportunities for growth. As such, businesses that are able to effectively leverage the technology are likely to gain a significant competitive advantage.

Not perfect but overwhelmingly impressive.

For us and many executives, we’ve spoken to recently, entering one prompt into ChatGPT, developed by OpenAI, was all it took to see the power of generative AI.

In the first five days of its release, more than a million users logged into the platform to experience it for themselves.

OpenAI’s servers can barely keep up with demand, regularly flashing a message that users need to return later when server capacity frees up.

Products like ChatGPT and GitHub Copilot, as well as the underlying AI models that power such systems (Stable Diffusion, DALL·E 2, GPT-3, to name a few), are taking technology into realms once thought to be reserved for humans.

Developers can adapt the models for a wide range of use cases, with little fine-tuning required for each task.

Generative AI promises to make 2023 one of the most exciting years yet for AI.

Pushing further into human realms

More than a decade ago, we wrote an article in which we sorted economic activity into three buckets—production, transactions, and interactions—and examined the extent to which technology had made inroads into each.

Machines and factory technologies transformed production by augmenting and automating human labour during the Industrial Revolution more than 100 years ago, and AI has further amped up efficiencies on the manufacturing floor.

Transactions have undergone many technological iterations over approximately the same time frame, including most recent digitization and, frequently, automation.

That’s not to say these tools are intended to work without human input and intervention.

Generative AI is also pushing technology into a realm thought to be unique to the human mind: creativity.

The technology leverages its inputs (the data it has ingested and a user prompt) and experiences (interactions with users that help it “learn” new information and what’s correct/incorrect) to generate entirely new content.

Business uses abound

These models are in the early days of scaling, but we’ve started seeing the first batch of applications across functions, including the following (exhibit):

  • Marketing and sales—crafting personalized marketing, social media, and technical sales content (including text, images, and video); creating assistants aligned to specific businesses, such as retail
  • Operations—generating task lists for efficient execution of a given activity
  • IT/engineering—writing, documenting, and reviewing code
  • Risk and legal—answering complex questions, pulling from vast amounts of legal documentation, and drafting and reviewing annual reports
  • R&D—accelerating drug discovery through a better understanding of diseases and discovery of chemical structures

Excitement is warranted, but caution is required

The awe-inspiring results of generative AI might make it seem like a ready-set-go technology, but that’s not the case. Its nascency requires executives to proceed with an abundance of caution. Technologists are still working out the kinks, and plenty of practical and ethical issues remain open. Here are just a few:

  • Like humans, generative AI can be wrong. ChatGPT, for example, sometimes “hallucinates,” meaning it confidently generates entirely inaccurate information in response to a user question and has no built-in mechanism to signal this to the user or challenge the result. For example, we have observed instances when the tool was asked to create a short bio and it generated several incorrect facts for the person, such as listing the wrong educational institution.
  • Filters are not yet effective enough to catch inappropriate content. Users of an image-generating application that can create avatars from a person’s photo received avatar options from the system that portrayed them nude, even though they had input appropriate photos of themselves.
  • Systemic biases still need to be addressed. These systems draw from massive amounts of data that might include unwanted biases.
  • Individual company norms and values aren’t reflected. Companies will need to adapt the technology to incorporate their culture and values, an exercise that requires technical expertise and computing power beyond what some companies may have ready access to.
  • Intellectual-property questions are up for debate. When a generative AI model brings forward a new product design or idea based on a user prompt, who can lay claim to it? What happens when it plagiarizes a source based on its training data?

Initial steps for executives

Given that generative AI is being considered by businesses, executives will want to establish a monitoring system as soon as possible to pinpoint the areas of their operations where the technology may have the greatest immediate impact. A no-regrets move is to assemble a cross-functional team, including data science practitioners, legal experts, and functional business leaders, to think through basic questions, such as these:

  • Where might the technology aid or disrupt our industry and/or our business’s value chain?
  • What are our policies and posture? For example, are we watchfully waiting to see how the technology evolves, investing in pilots, or looking to build a new business? Should the posture vary across areas of the business?
  • Given the limitations of the models, what are our criteria for selecting use cases to target?
  • How do we pursue building an effective ecosystem of partners, communities, and platforms?
  • What legal and community standards should these models adhere to so we can maintain trust with our stakeholders?

While this is happening, it’s crucial to promote deliberate innovation throughout the company by putting in place sandboxed environments for testing, many of which are easily accessible via the cloud, with more likely on the horizon.


Did you subscribe to our newsletter?

It’s free! Click here to subscribe!

Source: McKinsey

LEAVE A REPLY

This site uses Akismet to reduce spam. Learn how your comment data is processed.