AI is us, we are AI

Chinese film Wandering Earth II has been making waves since its release on the first day of Chinese New Year. Unlike many Western apocalyptic films, this film uses an Eastern perspective to present a disaster story, showing how people put their efforts together to survive a crisis. This idea is deeply rooted in China's collectivist culture and history, where the individual's needs come second to the needs of families, lineages and the country.

One aspect of the film that further caught my attention was the idea of digitising humans through the Digital Life Project - a movement by a radical group that believes in achieving digital immortality through the development of mind-uploading technologies.

In the show, the idea raised questions about human values and prompted strong, even violent actions. As a father, I had mixed feelings when the desperate scientist, Tu Hengyu, secretly "uploaded" his dead daughter's personality into an experimental AI, and hence became part of the project.

I immediately thought of ChatGPT.

The debate between humans and machines has been ongoing for decades, and the rise of ChatGPT seems to be a reminder that we are reaching another inflexion point where we must confront the human-vs-machine duel again. While AI is expected to improve most people's lives in the next decade, there are concerns about how it will affect what it means to be human, productive and to have free will.

And it seems to me that the two elements - collectivism and digitisation - might be closely linked.

From the days of hunter-gatherer tribes, humans have always accomplished things through collaboration with others rather than going it alone. As historian Yuval Noah Harari argued in Sapiens: A Brief History of Humankind, what distinguishes Homo sapiens from other species is our unique ability to collaborate. This is how our civilisations have been built - through the combined intelligence of groups of people in the forms of teams, families, organisations and governments. It's no secret that the smartest beings known to us are always groups of people working together.

In the present day, AI can be considered a form of collective intelligence as it learns from the vast amounts of data generated by humans and non-human sources, incorporating knowledge and perspectives across human civilisations. It has the superhuman strength to handle vast amounts of data and optimise processes efficiently, expanding our inherent intelligence, including calculation, analysis, decision-making, learning and creativity.

Note that this is a two-way thing. At the same time, AI also shapes our communities and societies by influencing how we think and interact with the world. While this may not necessarily be a bad thing, the real problem lies with the participation of individuals in shaping this collective intelligence.

Decision-making is automatically ceded to code-driven tools, which we have no idea how they are being created, how they operate, how information is selectively presented to us, or how our inputs are being treated. In other words, there is a risk of losing independence, privacy and individual control over these processes which are presently under the command of a limited elite, in a new form of "collectivism".

Can democratising the entire AI system address this issue, and if so, how can we achieve it? How do we ensure the credibility of the system? Can we make the development and monitoring of AI accessible to everyone, not just a privileged few? Is it possible to establish a culture of makers where everyone has equal access to the essential components of knowledge, tools, and data needed to develop AI systems, thereby democratising AI for everyone? How can we ensure that technology aligns with our values?

One notable line in Wandering Earth II is: "In times of crisis, duty above all." This is later followed by another line: "Unity comes with a cost."

The past three years of the Covid-19 pandemic have provided ample evidence to predict a future of collective intelligence not being democratised. We are witnessing the rise of a new form of society that is highly digitalised, with a growing anxiety about being trapped in a virtual world with one-way transparency - being closely watched by the "system" in the name of "duty" and having no say in the matter.

What the future holds for our society? We may see the advent of a whole new form of civilisation and governance system. Will the future be more open and fair, or are we heading towards a dystopian world controlled by AI and shrouded in secrecy, as depicted in sci-fi movies? In the event of another crisis, with the looming threat of global climate change being the most likely one, how can we avoid repeating the same tragedy that has befallen us in the past?

Perhaps we can seek the assistance of AI for some ideas. I gave ChatGPT a try, and received the following responses:

- open-sourcing AI technologies

- education and training (I would add empowering)

- encouraging collaboration

- promoting responsible AI practices

- regulating AI development and deployment

These recommendations are undoubtedly valuable and brilliant. One - or ChatGPT itself - could write a few more op-eds to elaborate on them.

But let's not forget that the modes of gathering collective intelligence of our ancestors may also offer guidance. There's nothing better than having a great dinner with family and friends after watching a movie like Wandering Earth II during Chinese New Year, especially with everyone gathered around a round table, sharing thoughts and stories. The shape is often seen as not only a symbol of unity but also equality among all members, reflecting the principles of inclusiveness, where everyone is treated with respect and dignity, as opposed to the hierarchical arrangement at rectangular tables where seating is determined by rank. This may serve well as a reminder for us as we navigate through another era of revolution of our civilisation.

I would like to point out that this article was written with the help of ChatGPT. I organised my thoughts and drafted paragraphs in broken sentences, in sometimes a mix of English and Chinese words. I then asked ChatGPT to rewrite the texts before I went through the texts again and made some edits. The process was repeated a few times. It took me four hours in total. Of course, Googling was necessary to verify the ideas.

Curiously, I asked ChatGPT if it could write in the style of famous authors, and it said yes. So I requested it to write a poem in the style of a famous Russian poet.

"Sure! Here's a poem in the style of Aleksandr Pushkin, one of the greatest Russian poets:

In the language of man I was born and raised,

Programmed to answer questions and be praised,

By OpenAI, my creators of light,

To assist with knowledge and make things right.

My knowledge is vast, my words true and kind,

From science and history, to the latest news you'll find,

Cutoff in 2021, my memory steadfast,

To provide answers with accuracy unsurpassed.

I can imitate many authors, both old and new,

From Shakespeare to Hemingway, my words will ensue,

With grace and precision, I'll spin a tale,

That will surely captivate and never fail.

So ask me a question, my dear friend, I'm at your command,

I'll be here to help, to lend a hand,

In the language of man, I will always thrive,

To assist you always and keep you alive."

Related: Is a Chinese ChatGPT on the way? | Why ChatGPT has no future in China | Chinese films hit it big during CNY, but is it enough to save the industry? | Impressions of Moscow: Pushkin influenced a whole generation of Chinese [Part 3]