November 25, 2024

Since ChatGPT first emerged in late 2022, there have been numerous columns offering advice on how to put ChatGPT to work in your business. While this advice is great for 2023, in 2024 it fails to harness the power that generative AI has to offer.

In a speech at ICNY, Dr. R. David Edelman, an MIT professor who served as technology advisor to three presidents, explained how we can best navigate what he calls the “dangerous pivot” currently taking artificial intelligence from the mainstream. Data turns to the field of artificial intelligence. Machine learning (in its “infancy”) to today’s generative artificial intelligence.

What exactly is artificial intelligence?

When I asked ChatGPT to provide Inman readers with a clear definition of artificial intelligence, its response was as follows:

“Artificial intelligence (AI) refers to computer systems designed to perform tasks that typically require human intelligence, such as recognizing speech, making decisions, and understanding natural language. It encompasses a range of technologies that enable machines to learn from experience and adapt to new input and perform human-like tasks, streamlining and enhancing every aspect of the job, including in real estate where it can analyze market trends, predict property values, and personalize customer interactions.”

Edelman described the role of artificial intelligence slightly differently:

“Artificial intelligence classifies large amounts of information, discovers subtle patterns and correlations, learns from behavior, and ultimately makes predictions based on machine learning (applied statistics),” Edelman said.

The key to understanding artificial intelligence, Edelman said, is that these systems are predictive machines, whether predicting what words will come next or predicting the meaning of a certain configuration of pixels.

In fact, almost everything we see in the media is about big data and machine learning.

“Most businesses are just crossing the Rubicon using big data and machine learning to try to make some predictions about what they do every day,” Edelman said.

It’s important to understand that “vanilla AI” has led to huge breakthroughs in a variety of fields, including education, reducing CO2 emissions by using machine learning to predict better bus routes in Boston, and preventing deaths from sepsis ( Sepsis mortality rate is 40%) rate.

Edelman said ChatGPT is experiencing what he calls a “dangerous pivot” where generative AI is transitioning from its infancy more than a year ago to “armchair AI” that can be done at home. “Edelman said.

“What I mean by generative AI is things like ChatGPT or Claude and image generators such as Dar ·E 2 or halfway,” Edelman said. (For a glimpse of the stunningly realistic images, click the link halfway.)

These new tools are highly advanced and represent the cutting edge of innovation. Tasks that once took a lot of time, resources, and millions of dollars’ worth of computers can now be done at home for as little as $10 to $50 a month.

Using generative artificial intelligence? Your job description is “BS Management”

Given the power of generative AI, a surprisingly small percentage of companies use it in customer-facing areas. Edelman attributes part of the problem to anxiety about the limits of generative AI. reason?

“The answer is that there is an anxiety, probably a legitimate anxiety, that creeps into the field with an appropriate awareness of the limitations of the system,” Edelman said.

“The best way to think about generative AI for your business is that it’s like an Ivy League intern who is very articulate, very confident, and completely filled with it ten percent of the time.”

In terms of using generative AI, “Now in managing generative AI, your job is bullshit management, specifically understanding what that 10 percent is and when it happens,” Edelman said.

“Sometimes they (generative AI systems) make mistakes, and the reason they make mistakes is because of inherent limitations of the technology because of how it works.”

future challenges

As the use of generative AI continues to grow, real-world problems we already face in real estate and other fields will explode in the coming years.

One of the most worrying examples is so-called deepfakes, where artificial intelligence can imitate sounds with remarkable realism. Scammers are now using these fake voices to authenticate wire transfers.

“It happens everywhere and you have to be aware of it,” Edelman said. “The answer isn’t lines of code, it’s smart organizational planning, thinking creatively like bad guys, and recognizing these relationships, especially in an industry as human as yours. These relationships are as fragile as the technology at your disposal ,” Edelman said.

How do we move forward?

At the beginning of the meeting, Edelman shared the following quote from science fiction author Arthur C. Clarke:

“Every sufficiently advanced technology is indistinguishable from magic.”

When something seems like magic and people don’t understand it or worry it’s beyond their comprehension, they may become frightened or try to push it away, Edelman said.

“These systems were designed by ourselves and had limitations that we knew we could actually work around and work around,” Edelman explained. “They have flaws that we can control. In other words, artificial intelligence is not magic, it’s math and coding.”

Hard choices must be made now

Edelman is laser-focused on the choices we need to make now about this technology and how it interacts with our lives and livelihoods.

We live in an environment where someone can steal your face and voice and use your identity without your permission. As we head into another election, Edelman said a survey shows only two to seven percent of companies are working on political stability or national security issues.

“So now at the enterprise level and at the human level, we have to decide what artificial intelligence should and shouldn’t do,” Edelman said.

The next big step: How to work with these machines

Edelman’s final piece of advice is to “work with AI, be smart about it, and don’t worry about AI taking your job,” but he then warns, “People who know how to use AI might.”

Just for fun, I visited ChatGPT, plugged in this article, and asked for comments on the Edelman conference. Here’s what Edelman had to say:

“As for the comments on Edelman’s recommendations, he seemed to provide a comprehensive and realistic assessment of the current and potential impact of artificial intelligence on various industries, including real estate. He focused on the importance of understanding the predictive nature of artificial intelligence as well as generating The difference between traditional AI and traditional data-driven AI is crucial for real estate professionals.

He rightly points out that AI should be viewed as a tool rather than a substitute for human expertise, and emphasizes the importance of managing its limitations while leveraging its strengths. “

Edelman provides a roadmap on what generative AI can do, but how to drive it to get the best results for your real estate business when old strategies in 2023 aren’t harnessing the full power of generative AI

Bernice Ross, President and CEO Brokerage UP and Real EstateCoach.com, is a national speaker, author, and trainer with more than 1,500 published articles. Learn about her sales training programs for new and experienced agents: BrokerUP.com Plus her latest initiative to help women build wealth and ensure their financial independence Women’s Wealth Real Estate Website