We propose a general framework for human-AI collaboration that amplifies the distinct capabilities of both types of intelligence. We refer to this as Generative Collective Intelligence (GCI). GCI employs AI in dual roles: as interactive agents and as technology that accumulates, organizes, and leverages knowledge. In this second role, AI creates a cognitive bridge between human reasoning and AI models. The AI functions as a social and cultural technology that enables groups to solve complex problems through structured collaboration that transcends traditional communication barriers. We argue that GCI can overcome limitations of purely algorithmic approaches to problem-solving and decision-making. We describe the mathematical foundations of GCI, based on the law of comparative judgment and minimum regret principles, and briefly illustrate its applications across various domains, including climate adaptation, healthcare transformation, and civic participation. By combining human creativity with AI's computational capabilities, GCI offers a promising approach to addressing complex societal challenges that neither humans nor machines can solve alone.

For entrepreneurial MIT students looking to put their skills to work for a greater good, the Media Arts and Sciences class MAS.664 (AI for Impact) has been a destination point. With the onset of the pandemic, that goal came into even sharper focus. Just weeks before the campus shut down in 2020, a team of students from the class launched a project that would make significant strides toward an open-source platform to identify coronavirus exposures without compromising personal privacy. Their work was at the heart of Safe Paths, one of the earliest contact tracing apps in the United States. The students joined with volunteers from other universities, medical centers, and companies to publish their code, alongside a well-received white paper describing the privacy-preserving, decentralized protocol, all while working with organizations wishing to launch the app within their communities.

I'm on the phone with a startup executive roleplaying as a frustrated customer, and a note along with a speedometer icon appears on my computer screen: Speaking slowly -- You are speaking slower than usual. Try increasing your speaking pace. I speed up, and the message disappears, only to be replaced with another: Continuous Speaking -- Finish your thought. Later, as the exec struggles to find the date of a made-up transaction, the software I'm using detects the strained note in his voice, and again decides I should intervene. A new message appears, this one accompanied by a pink heart: Empathy Cue -- Think about how the customer is feeling.

Deep learning is a powerful statistical technique for classifying patterns using large training data sets and multi-layer AI neural networks. It's essentially a method for machines to learn from all kinds of data, whether structured or unstructured, that's loosely modeled on the way a biological brain learns new capabilities. Machine learning can be applied to just about any domain of knowledge given our ability to gather valuable data in almost any area of interest. But machine learning methods are narrower and more specialized than humans. There are many tasks for which they're not effective given the current state-of-the-art.

Customer service calls can be ... infuriating. Part of the reason is that humans generally aren't great at reading subtle emotional cues, especially if we only have voice to go by. At the same time, we often inadvertently broadcast unintended emotional signals, easily leading to miscommunication and discomfort over the phone. But an MIT spinoff called Cogito is using voice analytics to help customer service reps better understand how customers are feeling. The technology behind Cogito's enterprise product, which can predict a customer's emotional state by analyzing tone and voice patterns, has also been used to identify signs of PTSD and depression in veterans.

In 1983, I gave the AAAI president's address titled "Artificial Intelligence Prepares for 2001." An article, based on that talk, was published soon after in AI Magazine. In this article, I retract or modify some of the points made in that piece and reaffirm others. Specifically, I now acknowledge the many important facets of AI research beyond high-level reasoning but maintain my view about the importance of integrated AI systems, such as mobile robots. In 1983, I gave the AAAI president's address titled "Artificial Intelligence Prepares for 2001."

AI researchers are interested in building intelligent machines that can interact with them as they interact with each other. Much effort has been expended on "automatic deduction of structure of a possibly dynamic three-dimensional world from two-dimensional images" (Nalwa 1993). There has been considerable progress in the areas of object recognition, image understanding, and scene reconstruction from single and multiple images. This progress, coupled with the improvements in computational power, has prompted a new research focus of making machines that can see people; recognize them; and interpret their gestures, expressions, and actions. In this article, I present methods that give machines the ability to see people, understand their actions, and interact with them.

In 2013, Alistair Shepherd asked everyone in a business-school pitch competition to complete a survey with questions inspired by online-dating sites. It asked things like "Do you like horror movies?" and "Do spelling mistakes annoy you?" Shepherd predicted how well the eight teams would collaborate internally and how they would ultimately fare. He ended up ranking all eight correctly. What made for a great team? Those in which people had the most tolerance for their teammates' perspectives--and those in which people had the greatest diversity in personalities. Mr. Shepherd's experiment represents an attempt to get beyond the usual approach to workplace chemistry.

Most organizations today aspire to use predictive analytics, artificial intelligence, and machine learning to influence customer behavior and improve business performance. Unfortunately, the process for becoming a "predictive organization" is broken from both a technical and an organizational standpoint. It requires "Unicorns:" Well trained, expensive, rare data scientists and PhDs who are hard to hire and retain. Those teams then invest roughly six months on average cleaning data and building machine learning models, and then have to maintain those models as they degrade over time. Whenever products and consumer behavior change, the models break and need to be re-written.

Despite the introduction of all sorts of new technology, a myriad of new channels and a host of self-service options, when things go wrong, get complicated or become difficult for customers most of them will want to pick up the phone and talk to another human being. That behaviour makes phone conversations an integral and hugely important part of the whole customer experience, whether the conversations take place at the beginning (sales), middle (service) or the end (renewal) of the customer's journey. However, the problem with phone conversations is that they don't always go as well as companies or customers would like. And, following a phone conversation it's not uncommon to hear phrases like: "It felt like they were more interested in selling me something rather than fixing my problem" So, in the midst of all the new and exciting technology that is emerging, it's exciting to see some technologists turning their attention to phone conversations and how companies can use advanced technology like artificial intelligence (AI), behavioural science, analytics and deep learning to help companies improve the conversations they have with their customers. Here are a couple of examples of two firms that I have come across in the last few weeks that are using advanced technology, in different ways and at different parts of the customer journey, to help improve conversations with customers.