TPU

Headlines · 3

1. 3d
   Alphabet Q3 growth highlights AI search monetization gap

   Alphabet reported Q3 2026 revenue of $127.6 billion, up 25% year over year, while Google Cloud revenue rose 103% to $30.71 billion. Search advertising revenue increased 12% to about $63.4 billion but missed Wall Street expectations. On the earnings call, Chief Business Officer Philipp Schindler said AI Mode has lower monetization than traditional Search. Google said it was scaling ads in both AI Mode and AI Overviews, with AI Mode ads rolling out in 10 countries. The company planned additional AI Mode expansions, including Brazil, Mexico and the United Kingdom, in Q4 2026.

   9to5Google · 🔥 52
2. Oct 17
   Anthropic offers Blackstone 10%+ yield on $60B TPU debt package

   Anthropic is pursuing roughly $60 billion in debt financing to buy Google tensor processing units (TPUs), split into about $42 billion of senior debt guaranteed by Broadcom and $18 billion of subordinated debt, according to multiple reports citing unnamed sources. To attract Blackstone to subscribe $9 billion of the subordinated tranche, Anthropic is offering a 10% coupon, with total returns higher after issue discounts and fees — versus 8.5% on a similar Anthropic bond about four months earlier. The reports say Bank of America, Citigroup and Morgan Stanley have begun syndicating the senior tranche, while Blackstone is expected to help distribute the remaining $9 billion of subordinated debt in coming months. Neither Anthropic nor Blackstone has publicly confirmed the terms.

   IT之家 AI · 🔥 0
3. Oct 13
   Custom silicon and the inference price war: Google's Argon undercuts rivals

   Citing Artificial Analysis data, Tomasz Tunguz notes that five frontier models sit within five intelligence points of one another while their cost per task differs by 3.8x; Google's Argon comes in at $1.99 a task, 74% below the priciest model, Fable 5.1, and 67% below Opus 5.5, 56% below Muse Wonder and 39% below Astra. He attributes the gap to differences in architectures and GPU costs, pointing to Google's TPU program begun in 2013 and citing Google's own TPU v4 measurements versus Nvidia's A100. The essay also cites Microsoft's Maia 300 and OpenAI's first inference chip, Jalapeño, both company-reported efficiency claims without independent verification, and estimates Google could serve tokens at 44% less than peers — a figure derived from the midpoint of a published range, not a measured result.

   Tomasz Tunguz · 🔥 0

Experience and discussion from the community

Share my TPU experienceAsk about TPU