This article is adapted from Oversharing, a newsletter about the sharing economy. Self-driving cars have met their match in the form of the humble traffic cone. If you're on TikTok, you may have seen what I'm talking about: a viral video of San Francisco activists disabling autonomous Cruise and Waymo vehicles by placing bright orange traffic cones on their hoods. This content requires consent that you have not granted on Slate. To view this content please visit www.tiktok.com

A newly discovered network of'lost' ancient cities has been discovered in the Amazon, using lidar technology – dubbed'lasers in the sky' – to peer through the tropical forest canopy. The cities, built by the Casarabe communities between 500-1400 AD, are located in the Llanos de Mojos savannah-forest, Bolivia, and have been hidden under the thick tree canopies for centuries. They feature an array of elaborate and intricate structures unlike any previously discovered in the region, including 16ft-high terraces covering 54 acres – the equivalent of 30 football pitches – and 69ft-tall conical pyramids. The international team of researchers from the UK and Germany also found a vast network of reservoirs, causeways and checkpoints, spanning several miles. The discovery challenges the view of Amazonia as a historically'pristine' landscape, the researchers say, showing it was instead home to an early'urbanism' created and managed by indigenous populations for thousands of years.

Machine learning is helping urbanists confirm–or disprove–long-standing theories about cities. Why do certain neighborhoods feel safe while some feel dangerous? Why are others considered beautiful? How do cities develop and change over time? And most importantly, how can we quantify these observations about the way we perceive cities, and use it to plan urban areas that are more equitable?

AI developments on smart cities, if not critical, risk making a flawed urban model more efficient. Instead, we suggest that AI should challenge the mainstream techno-optimistic approach to solving urban problems by dialoguing with other academic fields, questioning the dominant urban paradigm, and creating transformative solutions. We claim that doing differently, rather than doing better, may be smarter for cities and the common good. This article is part of the special track on AI and Society.

Last June Volume, a leading magazine on architecture and design, published an article on the GoogleUrbanism project. Conceived at a renowned design institute in Moscow, the project charts a plausible urban future based on cities acting as important sites for "data extractivism" – the conversion of data harvested from individuals into artificial intelligence technologies, allowing companies such as Alphabet, Google's parent company, to act as providers of sophisticated and comprehensive services. The cities themselves, the project insisted, would get a share of revenue from the data. The company does take cities seriously. Its executives have floated the idea of taking some struggling city – Detroit?

Why do certain neighborhoods feel safe while some feel dangerous? Why are others considered beautiful? How do cities develop and change over time? And most importantly, how can we quantify these observations about the way we perceive cities, and use it to plan urban areas that are more equitable? César Hidalgo, the director of the Collective Learning group at the MIT Media Lab, has spent years using crowdsourced data and machine vision technology to build models of cities that can answer questions that statistics and surveys simply can't.