Google unveiled two systems for its eighth-generation TPU lineup: TPU 8tx, designed to protect sensitive data during AI processing, and TPU 8i Max, designed for memory-intensive AI tasks. Google did not disclose pricing or availability dates. Its performance figures compare the new systems with earlier Google hardware, not Nvidia’s latest products.
Google says TPU 8tx uses hardware-level protection to isolate customer data and model parameters while they are in use. That protection cannot stop a poorly designed AI agent from mishandling data it is allowed to access. TPU 8i Max combines two TPU 8i chips, doubling memory throughput and other resources compared with TPU 8i. Google also said it is open-sourcing TPU Sync software, which it claims can cut certain data-transfer delays and response startup times by more than 90%.
