As we shared previously here, ChatGPT’s conversational responses to our questions goes beyond authoring a blog post, writing code or serving as a ghost writer for a student’s research paper. We identify why the technology has the potential of upending how we perform a web search or voice search and is viewed by Google as potential threat to its $168 billion dollar plus ad revenue business.

For the past 20+ years, Google has seemed relatively untouchable when it comes to owning the ad search business. As of November 2022, Google handled more than 90% of all search queries, with Bing following way behind at 3.42% and Yahoo at 1.23%. In 3Q22, Google accounted for $39.5 billion in ad search revenue. If you consider what a 5%-8% piece of that could be worth in terms of lost profit for Google, it’s not surprising that the company has sounded the alarm about how ChatGPT could impact its ad revenue business. This is despite the fact that Google has been “building similar natural language models such as LaMDA, which stands for Language Model for Dialogue Applications,” leaving Google executives and employees asking if it is still the industry leader here and whether it’s a missed opportunity for the company.

“In 3Q22, Google accounted for $39.5 billion in ad search revenue.

 

If you consider what a 5%-8% piece of that could be worth in terms of lost profit for Google, it’s not surprising that the company has sounded the alarm about how ChatGPT could impact its ad revenue business.”

Conversational Search vs. a Single Question

The author of this post asked ChatGPT if it was a good alternative to Google as a search engine, and ChatGPT answered:

“One potential advantage of using ChatGPT as a search engine is that it is able to provide more personalized and conversational results. Because ChatGPT is a language model, it is able to understand and respond to natural language queries, allowing users to ask questions and receive answers in a more intuitive and human-like way. This can make the search experience more engaging and interactive, and may be especially useful for users who have specific or complex information needs.”

“On the other hand, there are also potential limitations to using ChatGPT as a search engine. Because it is a large language model and not a traditional search engine, ChatGPT may not have access to the same breadth and depth of information as other search engines. This means that it may not be able to provide as comprehensive or up-to-date results, and may not be as effective for certain types of searches, such as those that require a large amount of data or real-time information.”

“Conversational search is extremely difficult to monetize. If a search only yields a single result, then having that result be paid for or sponsored would be hugely damaging to user trust.”

As per ChatGPT’s response above, the biggest advantage that generative AI has is the ability of users not only to ask it a question, but to ask follow-up questions that go deeper into the answer in conversational format. When I asked Google the same question, It came back with several article titles about the subject with page links. For me to really dive into the answer, I would have had to read through several pages, which would inevitably be followed by new queries.

The biggest drawback for generative AI users, which I’m sure will be addressed sooner than later, is that it can’t provide web links that refer back to the source of the information. Once this has been addressed in both the web format and voice technology, it will be another major technology leap for AI.

Another issue is how can this be monetized? Google’s search engine business is built on advertisers paying for and bidding on keywords and ads driven by search marketers. This is explained further here. “Conversational search is extremely difficult to monetize. If a search only yields a single result, then having that result be paid for or sponsored would be hugely damaging to user trust.” Search advertising is only effective when the searcher has a choice of results, which gives them the option to click or not click on a sponsored result. Onlookers have correctly identified that following in the footsteps of ChatGPT would be a disaster for Google’s business model.”

The author also identified this AI platform, Andi Search, as delivering the “best of both worlds” between chat-based conversational search and results-based web search that combines conversational chat responses and links to learn more. So, apparently, we may not be that far off from having the ideal form of search.

So Why Hasn’t Google Developed This?

“Google may be reluctant to deploy this new tech as a replacement for online search, however, because it is not suited to delivering digital ads, which accounted for more than 80% of the company’s revenue last year.”

This New York Times article provides some additional background about Google’s involvement with ChatGPT and the reason why it hasn’t pursued it more aggressively.

“Google has spent several years working on chat bots and, like other big tech companies, has aggressively pursued artificial intelligence technology. Google has already built a chat bot that could rival ChatGPT. In fact, the technology at the heart of OpenAI’s chat bot was developed by researchers at Google.

Google may be reluctant to deploy this new tech as a replacement for online search, however, because it is not suited to delivering digital ads, which accounted for more than 80% of the company’s revenue last year.”

As we touched upon in our previous post, Will AI Fundamentally Change The Way We Work and Create?,  we brought up the danger of how these chat bots may not always be 100% accurate and might provide results that are discriminatory, biased towards women and race, or may contain language that is inappropriate or hateful.

The Potential of Voice Technology

If there’s one area that I’m most excited about, it’s how chat bots can redefine voice search, e.g., Siri and Alexa. We’ve all seen the Iron Man movies where Tony Stark has a very realistic exchange with his computer, J.A.R.V.I.S. (which stands for Just A Really Very Intelligent System). What if Siri or Alexa became just as intelligent and didn’t just provide simple answers to your questions? Instead, what if you were able to have an ongoing dialogue with follow-up questions to their answers? It’s clear that generative AI has the potential to change voice search, among other things, and to address this in the near future.

Think about how this could be applied to the healthcare or the mental health space, i.e., as a companion to the patient who is not only there for conversation, but for 24/7 monitoring of the patient’s wellbeing.

The AI Boom Is Very Real

As I completed this post, The New York Times reported here that the creator of ChatGPT, OpenAI, “is in talks to complete a deal that would value it at around $29 billion, more than twice its valuation in 2021. This type of A.I. promises to reinvent everything from online search engines like Google to photo and graphics editors like Photoshop to digital assistants like Alexa and Siri. Ultimately, it could provide a new way of interacting with almost any software, letting people chat with computers and other devices as if they were chatting with another person. In 2022, investors pumped at least $1.37 billion into generative A.I. companies across 78 deals, almost as much as they invested in the previous five years combined, according to data from PitchBook, which tracks financial activity across the industry.”

To fully understand the power and potential of AI, see for yourself (for free!) by visiting here, to experiment with queries, and here, to experiment with image creation.

Then think about how each of these tools can improve—or disrupt—what you do, your business, industry, or our everyday lives. It’s both fascinating and very real.

Please reach out to me with any questions by emailing me here. As always, thank you for reading.

Photo by Jonathan Borba on Unsplash