Google plans first test ofAl chips in space under Project Suncatcher (blog.google)

Google has unveiled Project Suncatcher, an ambitious initiative aimed at scaling machine learning capabilities in space by deploying solar-powered satellites equipped with Tensor Processing Unit (TPU) AI chips. This project seeks to explore how AI can be utilized to address some of humanity's most pressing challenges, leveraging the immense energy from the Sun to power a network of interconnected satellites. Initial research has already been published, detailing the design, control, and communication strategies for these satellite constellations, along with preliminary findings from radiation tests on the TPUs. This development is significant for the AI/ML community as it opens new frontiers for computational resources beyond Earth, potentially allowing for massive parallel processing capabilities and real-time data analysis in space. Google's next step involves a partnership with Planet to launch two prototype satellites by early 2027, which will serve as a learning mission to test the hardware's performance in orbit. If successful, Project Suncatcher could herald a new era of advanced AI applications and research opportunities in extraterrestrial environments.