Google Sends AI Chips to Space in Groundbreaking Experiment

Google is taking its AI computing hardware to new heights, literally. As part of Project Suncatcher, an experimental program examining the feasibility of large-scale machine learning infrastructure in space, Google has scheduled a prototype satellite carrying its Tensor Processing Units (TPUs) for launch as early as September 24.

The mission aims to test whether specialized AI chips can survive and operate under the harsh conditions of low Earth orbit, including radiation, temperature extremes, and physical forces. The experiment will also study cooling methods, as conventional airflow cannot cool processors in space's vacuum.

Google has described Project Suncatcher as a long-term research effort rather than an imminent commercial data center service. One attraction is the abundant solar energy available to satellites in orbit, potentially powering AI computing. However, substantial obstacles remain, including launch costs, radiation exposure, thermal management, and the complexity of producing and maintaining computing infrastructure in space.

The first mission is designed to collect engineering data and identify potential failures rather than operate as a functioning orbital data center. Google plans further tests involving high-bandwidth optical links between satellites, exploring whether multiple spacecraft could eventually operate together as an interconnected AI computing cluster.