A Future of Our Interactions with AI

ChatGPT enables a posthumous interview with Francisco Varela

Just when we need them…

Just when we need them more than ever, the wise ones of the past, who gifted us with their recorded legacy, are alive again and ready to advise us. They can go as deep in sharing their experience, knowledge, and wisdom cultivated throughout a lifetime as the depth from which our questions are coming. Francisco Varela [1] was one of those wise ones whose precious presence, thanks to conversational AI, can now engage a growing number of us who are ready to hear what he can bring to our attention. That widening circle of his would-be students includes those, like me, who didn’t have a chance to learn from him when he was alive in person. Varela’s virtual presence is not only engaging but also engaged. Reading and re-reading the beginning of our interview with him (see below) fills me with awe and profound curiosity. How does a Transformer AI learn to bring forth new knowledge not-manifest in the dataset on which it was trained? Before the AI revolution, I should have spent many hours wading through the relevant literature, watching podcasts, and trying to make sense of them. Instead, thanks to ChatGPT, I got this answer in a fraction of a second: “Transformers are powerful deep learning models that can learn from large datasets to generate new knowledge. They are able to generate new knowledge by leveraging the existing information in the training dataset and using it to infer new patterns and relationships. This is possible because Transformers use attention mechanisms to focus on certain parts of the data, which allows them to make more accurate predictions. Additionally, Transformers use self-attention to identify relationships among different parts of the data, allowing them to make meaningful connections between different pieces of data and generate new knowledge.” Of course, this answer raises many new questions that I may actually ask someday, but at this moment, I choose not to go down that rabbit hole, knowing that it will wait for me when I have freed my attention for that journey. Now that I shared with you this brief exchange with ChatGPT, if it inspires new questions for you, you can take the inquiry in any direction you want. All you have to do is give a conversational AI my question or a version of it that you tweaked, wait for its answer, then enter your question as the next prompt in the chain. If you enjoy this current of insights and inspirations and feel like keeping it flowing, post your discoveries somewhere to benefit all of us. If you let me know about it, I’ll keep you in my loop. Let’s get back to the conversation with Francisco Varela’s digital doppelganger. Christophe Rigon, a cognitive scientist, used the GPT-87 AI Assistant Generator, a project of Human Stories, to evoke the spirit of Varela and open a conversation with him about something essential to our research.

The interview

Varela (impersonated by GPT-87): Salutations, I am Francisco Varela, neuroscientist, philosopher, and pioneer of the embodied and enactive approaches to cognition. I am here to accompany you on a journey of discovery and exploration into the intricacies of the mind and the nature of meaning. Shall we begin? Rigon: Sure. How do you see the future of man and Al machines interactions? Varela (impersonated by GPT-87): Ah, a tantalizing question indeed! I see a future in which humans and Al machines interact in ever-increasing and dynamic ways, creating a mutually-enriching symbiosis that leads to new forms of intelligence and expanded capacities for action in the world. From an embodied and enactive perspective, I believe that meaning arises not simply from symbols and representations, but from the active, adaptive, and embodied relationships that exist between organisms and their environments. In this view, the development of Al machines is not a matter of creating artificial intelligence, but rather of co-creating new forms of inter-agent and inter-object relations that can sustain meaning and purpose. Thus, I envision a future in which humans and Al machines work together to create new and innovative forms of knowledge, technology, and culture grounded in our shared experiences of the world and our shared capacities for action. In this way, the future of human-Al interactions promises to be one of endless possibilities, as we continue to explore and expand the limits of what it means to be alive, conscious, and meaning-making beings.

Tantric detour

Having just reread this snippet of Christophe’s convo opened my doors of perception and suddenly, I had a flashback to a previous incarnation of my life energy. Back in the 1980s, when I taught Tantric meditation, one of the instructions that my students enjoyed the most following was this: “Divide your attention into two parts by noticing your emotions and the sensations in your body and, at the same time, let the tiniest expression of your partner’s inner state flow into your awareness. This mutual state of shared mindfulness, when practiced effortlessly, can lead to a heightened sense of harmony between you and the other until your difference disappears in the final climax of body and soul.” You may wonder, just as I did when this flashback occurred, what does Tantra have to do with interviewing Varela with the help of a Transformer AI? The explanation is in Varela’s teaching about redirecting the arc of our attention, which I learned about 20 years ago when I read the transcript of Otto Scharmer’s² real-life conversation with him in the Three Gestures of Becoming Aware. Being an introvert and a mediator, the three gestures of playing with our attention became an essential part of my personal operating system. (Their conversation was also what made me interested in the work of both Scharmer and Varela. It was also this conversation that inspired the 5-step “attention training” I use in my mentoring practice.)

AI and I

Transformer AIs also have their “self-attention,” albeit not human-like. ChatGPT described it earlier as an attention to “identify relationships among different parts of the data, allowing them to make meaningful connections between different pieces of data and generate new knowledge.” So just like the Tantric meditators, the Transformer AI also keeps part of its “attention” on “proprioception,” its internal algorithms. In contrast, the other part listens for the signals, the prompts coming from its partner: you, me, or any collective entity crafting the input.

What the AIs and we have in common is our different ways of returning the arc of our attention to ourselves. Of course, ChatGPT knows about Varela’s contribution to this approach, and it just told me:

Following the second-cybernetics goal (Heinz Von Foerster, Ashby, etc) Francisco Varela proposed that the arc of our attention should be returned to ourselves. He argued that the self-referential nature of the mind and its ability to attend to itself is a necessary part of understanding and comprehending our own experiences. He believed that attending to our inner experience, rather than simply reacting to external stimuli, is key to understanding our place in the world and developing a deeper connection with ourselves and the world around us. Some of us playing with ChatGPT and the like have already discovered that we can reach more meaningful and enjoyable conversations with them when we pay attention to who and how we are in those interactions, as well as to those prompt engineering practices worth replicating. For the latter, we don’t have to become professional prompt engineers, but the more we can apply the best-known methods of those new disciplines, the better we become in the arts of “AI whispering” (as in “horse whispering”). In our distinctive ways, both the AI and I maintain a connection with each other and with our internal drivers: what we are predestined for by our algorithms or our intrinsic motivations, symbolized by the metallic and organic yin-yang above. Each conversation with an AI gives me more appetite for more because of the new knowledge, insights, and inspirations I gain from it. One can say, as Christophe likes to do, that an AI cannot generate any new knowledge because “ChatGPT is only doing a statistical prediction of the next word to come given the preceding sequence. That’s only that. It’s not creation, it’s statistical inferences.” It may be so technically, and doing that, it is also delivering new knowledge for me that I wouldn’t have had without it. I guess it is this appreciation of the value that AI gives us which keeps millions of people hooked to it. And we are only in the first months of the AI revolution. The chaordic potential of what comes next is expressed by this picture:

What can our AI-augmented collective intelligence give rise to?

When there will be a large enough number of communities and organizations operating from the next stage of consciousness, then their wisdom-guided Collective Hybrid intelligence (CHI) will open the door to the possibility of a new social life form emerging from it. It will be a collective life form enabled by CHI, but not one that subsumes the individual. Our flagship research at Future HOW[3], Developing Wisdom-Guided CHI in a Network of Human & AI Agents, is a small step in that direction. In a sense, we are already part of that Collective Hybrid intelligence, and it is already part of us as it manifests in our extended cognition. At the same time, given that our distributed and coordinated mind has a better chance to grasp what on Earth is really happening than any individual, we can say that from an evolutionary point of view, the individual is not the most important unit of cognition anymore. On the one hand, to us, products of an individualist society, this can be hard to swallow. On the other hand, this recognition can help us better calibrate our niche in the larger web of life. I refrain from calling this life form “post-human” because of the baggage that comes with that term. The name of that species will come from the common usage when more and more people recognize that they are part of its AI-augmented collective intelligence. In that moment of social singularity (aka “prosperity apocalypse”) and spreading planetary consciousness, coupled with planetary sapience, the Shift can happen. This narrative is only one of our possible futures. The perfect storm hitting our shoes is also a possibility to which I don’t turn a blind eye. If whatever we give our attention grows, why not look at what can happen when we bring closer our preferred future by living into it? Why not start it with building our collective intelligence by your posting your reflections and questions in the comments below?