Skip to main content

Google's new processor fast-forwards machine learning technology

Google has unveiled a custom chip created specifically to facilitate projects related to machine learning and artificial intelligence. The company is calling the chip a Tensor Processing Unit, or TPU, in reference to the fact that it has been tailored to work with its TensorFlow machine learning API.

A blog post published by hardware engineer Norm Jouppi reveals that the TPU started its life as a “stealthy project” several years ago. The technology has now been implemented in Google’s data centers for more than a year, and it appears that the chips offer distinct advantages over standard processors.

Recommended Videos

Google claims that its TPUs offer “better-optimized performance per watt for machine learning.” Jouppi goes on to state that the chip is “roughly equivalent to fast-forwarding technology about seven years into the future.”

TPU was built from the ground up with machine learning in mind, utilizing a design that makes the chip better suited to the reduced computational precision of its intended application. The processor requires fewer transistors per operation, which allows it to accomplish more operations per second.

Google claims that it only took 22 days from the first test of TPU hardware to implement the processors in its data centers, running applications at speed. The technology has since been used to help improve several of the company’s most popular services.

TPUs have apparently helped improve the accuracy of maps and navigation aids offered via Street View, as well as the relevancy of search results thanks to their application on the RankBrain project. TPUs also helped give the AlphaGo computer program the thinking power it needed to defeat Go world champion Lee Sedol earlier this year.

Google intends to become an industry leader in machine learning, and wants to share its capabilities with its customers. To that end, the company open-sourced TensorFlow late last year — but it remains to be seen whether or not this hardware will remain an internal innovation.

Brad Jones
Brad is an English-born writer currently splitting his time between Edinburgh and Pennsylvania. You can find him on Twitter…
Google’s AI agent ‘Big Sleep’ just stopped a cyberattack before it started
Sundar Pichai

Google's AI agent, dubbed Big Sleep, has achieved a cybersecurity milestone by detecting and blocking an imminent exploit in the wild—marking the first time an AI has proactively foiled a cyber threat. Developed by Google DeepMind and Project Zero, Big Sleep identified a critical vulnerability in SQLite (CVE-2025-6965), an open-source database engine, that was on the verge of being exploited by malicious actors, allowing Google to patch it before damage occurred. “We believe this is the first time an AI agent has been used to directly foil efforts to exploit a vulnerability in the wild,” the company said.

Why it matters: As cyberattacks surge—costing businesses trillions annually—this breakthrough shifts defense from reactive patching to AI-driven prediction and prevention. It gives security teams a powerful new tool to stay ahead of hackers, potentially saving devices and data worldwide. CEO Sundar Pichai called it "a first for an AI agent—definitely not the last" according to Live Mint.

Read more
Google confirms merging Chrome OS and Android into one platform
Google Chrome app on s8 screen.

Why it matters: Google's push to blend Chrome OS and Android could supercharge affordable laptops like Chromebooks, making them more versatile for work and play. This move echoes Apple's seamless ecosystem across iPadOS and macOS, potentially shaking up the PC market where Windows dominates but innovation lags.

What's happening: In a bombshell interview, Google's Android ecosystem president Sameer Samat outright confirmed the company is "combining Chrome OS and Android into a single platform. This follows months of rumors and aligns with Android 16's new desktop-friendly features, like proper windowing and external display support. But then Samat later clarified on X that it's not a full-on merger killing Chrome OS; instead, it's about weaving Android's tech stack deeper into Chrome for better app compatibility and hardware efficiency.

Read more
WeTransfer backlash highlights need for smarter AI practices
A pair of hands using a keyboard on a laptop.

A recent update to WeTransfer’s terms of service caused consternation after some of its customers feared that it meant content from files uploaded to the popular file-sharing service would automatically be used to train AI models.

But the Netherlands-based company insisted on Tuesday that this is not the case, saying in a statement that it "does not sell user content to third parties,” and nor does it "use AI in connection with customer content.”

Read more