Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence

"Kate is a wonderful academic, really brilliant, and she has taken a look at the technology of artificial intelligence . In her view, it’s neither artificial nor particularly intelligent. Its use often masks a set of industrial processes and complex supply chains that bury within them deep inequalities and disparities in power. “We’ll always be a high tech society because we can’t put the genie back in the bottle” What she aims to do in the book is use this structural and political analysis to bring to the fore what happens behind what we think of as the ‘magic’ of our phones opening up when they see our faces. An example of that in Kate’s book is that a lot of the AI systems that we use today have required these systems to be trained by humans. The humans who do the training are often in emerging markets or poor economies, not being paid very well to go through the slightly mind-numbing task of training a machine to recognise what a dog is, and what a cat is. That’s just one example that she brings up. I found the book really thought-provoking and challenging—although I don’t agree with every part of her analysis. In the explanation of the symptoms, she also talks about the way in which those symptoms emerge. From that, you can see what types of policies you could enact to address them. But I think a large part of this is about transparency, and letting people be aware of how their products get to their table. One of the things that Kate identifies for us is something that we’ve become very easy with—how other products get to us. For example, when we have a hamburger delivered at home on a weekend, we never give a moment’s thought as to how that was produced and delivered from farm to plate. AI is often presented, in Kate’s view, as a magical technology. Her point is that, actually, behind it are a lot of structures of labour and resource extraction and resource use and power disparity that perhaps we should think about."

"I’ve deliberately chosen books that are looking at quite different aspects of AI because one of the questions is what we even mean by AI. How do we think about it? How do we conceptualize it and what it is? Then there are particular questions about the minutiae of how the technology works. One of the things I really like about Kate Crawford’s book is that she’s looking critically at the way the entire system of AI works and the impact of AI on a global scale. So we can think about AI just in terms of the software, what it’s capable of doing. That’s one element of it. But AI is not just software floating around in the ether, it’s actually manifest in hardware, in technology, in data banks, and also in a massive amount of human labor around the world. She looks at questions like mining and workers employed in terrible conditions for very little money. She also looks at the whole ideology behind AI and technology. Notions of efficiency that might be applied to machines, are now coming into the workforce. There are questions about surveillance of workers and concern about how employees at places like Amazon and Uber, but also elsewhere, are being tracked. It’s technology that is enabling us to do it. A lot of that technology is not AI, per se. It’s not a super intelligence. But it is the logic of the technology, the idea that we have to increase outputs and efficiency. Workers are being treated like machines. She’s focused on trying to understand and analyze the issues, so that people really understand the questions. Also, the depth of the problem. One of the main reasons why AI has developed so fast in recent years is because it relies upon masses and masses of data. There’s now an unbelievable amount of data available and it’s being collected all the time. She looks at the assumptions driving it. Can we simply understand the material world around us through data? Can we really understand human beings through data? What is it to be a human being just understood through data that’s being collected around us? So those are issues I think are really important to understand and how they’re embedded into the technology. Also, any philosophers interested in this will see immediately that collecting data assumes a process of classifying the world. You’re classifying the data in certain ways. That raises powerful issues about how we’re even being seen. She’s also got a chapter looking at affect. This is about using AI to detect our emotions, and then maybe also to manipulate them. That is based on work about how we can interpret human emotions which has also come under considerable critique. The subtitle is ‘Power, Politics, and the Planetary Costs of Artificial Intelligence.’ One of the things I like about it is that it’s very readable. She tells stories about how she drove to this place out in the middle of a desert where there are data centers. She’s taking you on journeys to different places around the world and within workplaces. In a sense, it’s really heavy reading, because it’s serious stuff, but it’s easy to read. She makes it really accessible."