Ironwood, our latest TPU(blog.google)

44 points by zdw 11 months ago | 8 comments

Gemini 2.5(blog.google)

910 points by meetpateltech 1 year ago | 450 comments

Google blog post announcing Gemini 2.5 Pro Experimental, a thinking model that leads common benchmarks with strong reasoning and coding capabilities.

Our eighth generation TPUs: two chips for the agentic era(blog.google)

420 points by xnx 6 months ago | 209 comments

Google blog post announcing its eighth-generation TPUs, TPU 8t and TPU 8i, custom AI chips designed for training and agentic inference at scale.

The AI magic behind Sphere's upcoming 'The Wizard of Oz' experience(blog.google)

42 points by radeeyate 1 year ago | 36 comments

Gemini 3(blog.google)

1638 points by preek 11 months ago | 1015 comments

Google blog post by Sundar Pichai and Demis Hassabis announcing Gemini 3, described as Google's most intelligent AI model.

Google changes its search box(blog.google)

651 points by berkeleyjunk 5 months ago | 891 comments

Google Keyword blog post announcing new AI features and agents in Search and a redesigned AI-powered search box, presented at I/O 2026.

TPU Deep Dive(henryhmko.github.io)

392 points by transpute 1 year ago | 80 comments

A personal blog post giving a technical deep dive into Google's TPU architecture, its hardware/software co-design, and how it differs from GPUs.

TPUs vs. GPUs and why Google is positioned to win AI race in the long term(uncoveralpha.com)

375 points by vegasbrianc 11 months ago | 278 comments

A Substack deep dive from UncoverAlpha on Google's TPU chips, covering their technical design, strategic position versus GPUs, and financial implications for AI inference.

Google open-sources TorchTPU, a native PyTorch back end for TPUs(github.com)

366 points by ilreb 6 days ago | 90 comments

GitHub repository for TorchTPU, Google's open-source native PyTorch backend for running models on Cloud TPUs.

Google's First Tensor Processing Unit: Architecture(thechipletter.substack.com)

324 points by c_joly 2 years ago | 172 comments

A Chip Letter Substack post examining the architecture of Google's first Tensor Processing Unit (TPU v1), following an earlier post on its origins.

TurboQuant: Redefining AI efficiency with extreme compression(research.google)

495 points by ray__ 7 months ago | 134 comments

Google Research blog post introducing TurboQuant, a method for extreme compression to improve AI model efficiency.

The HTML-in-Canvas API origin trial(developer.chrome.com)

110 points by andrewstuart 3 days ago | 54 comments

Chrome for Developers blog post introducing the HTML-in-Canvas API origin trial, which lets developers draw interactive DOM content into 2D canvas and WebGL/WebGPU textures.