{
  "id": 19193218,
  "title": "Google Unveils Two New Specialized AI Chips to Widen Its Challenge to Nvidia",
  "url": "https://urgent.news/2026/11/09/google-unveils-two-new-specialized-ai-chips-to-widen-its-challenge-to",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-09T18:00:00.000Z",
  "source": {
    "name": "Slashdot",
    "slug": "slashdot",
    "url": "https://tech.slashdot.org/story/26/11/09/1721229/google-unveils-two-new-specialized-ai-chips-to-widen-its-challenge-to-nvidia"
  },
  "original_language": "en",
  "account": "Google is expanding its AI chip lineup with two new specialized TPUs set to arrive next year, according to Quartz. The TPU 8tx and TPU 8i Max are designed to deepen Google's competition against Nvidia as demand for its chips outpaces supply. Both models are reconfigured versions of existing silicon, not new designs, according to Amin Vahdat, Chief Technologist for AI & Infrastructure at Google. The 8tx is intended for privacy-focused tasks, such as those handled by clients in regulated industries, and encrypts data at the chip level, said Vahdat. This stands in contrast to traditional methods where data is decrypted in memory as the machine works on it. In contrast, the 8i Max is aimed at AI applications requiring long context windows, making it particularly useful for complex tasks like drug discovery, math, and coding. Both chips are capable of handling increased workloads due to the additional processing power and memory provided by the 8i Max, which combines two TPU chips. Google's strategy follows a trend of releasing two TPU models a year, according to Bloomberg. Vahdat emphasized that by creating specialized versions of the chips, Google can provide greater value to customers than by trying to address the entire market with a single chip.",
  "summary": "Google is expanding its AI chip lineup with two specialized TPUs arriving next year: the TPU 8tx, which encrypts sensitive data at the chip level for confidential computing, and the TPU 8i Max, which combines two TPU chips to provide more processing power and memory for long-context workloads. The move broadens Google's challenge to Nvidia as demand outstrips supply, with Google saying every TPU…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}