DARK SECRETS: 5 - The Real Truth

Pizza-sized chips are the future of AI accelerators, researchers concur - but heat remains a huge problem

New study shows wafer-scale processors may outperform GPUs in both computing power and sustainability.

TechRadar · Jun 25, 2025

World's largest AI chip maker hit by crypto scam - Cerebras says token isn't real, so don't fall for it

$CEREBRAS is not a legitimate cryptocurrency – Cerebras' X account got hacked to push a fake coin, execs confirm.

TechRadar · Jun 20, 2025

Maker of world's largest AI chips was hit by a crypto scam — Cerebras confirms coin launched in its name is fake, X account retaken after being compromised by hackers [Updated]

Cerebras, maker of the world's largest AI chips, has had its X account compromized by a crypto scam, which also involves the launch of a fraudulent coin.

Tom’s Hardware · Jun 19, 2025

DeepSeek on steroids: Cerebras embraces controversial Chinese ChatGPT rival and promises 57x faster inference speeds

Cerebras brings its massive inference waferscale chip to DeepSeek R1 70B.

TechRadar · Jan 30, 2025

These AI startups eyeing IPOs could be poised for long-term investor success

Some AI startups are itching to finally go public; other tech startups that are just 'AI-adjacent' are hoping the tech can boost their share prices.

Fortune · Jan 30, 2025

Three chip leaders on what drives them to compete against $3 trillion Nvidia — and where the opportunity is

AMD, Cerebras Systems, and Altera executives explain the importance of competition in the chips world at Fortune’s Brainstorm AI in San Francisco on Tuesday.

Fortune · Dec 11, 2024

Nvidia's closest rival once again obliterates cloud giants in AI performance; Cerebras Inference is 75x faster than AWS, 32x faster than Google on Llama 3.1 405B

Cerebras Inference leads in AI performance; 75x faster than AWS, 32x faster than Google on Llama 3.1 405B.

TechRadar · Dec 2, 2024

Cerebras video shows AI writing code 75x faster than world's fastest AI GPU cloud — world's largest chip beats AWS's fastest in head-to-head comparison

Llama 3.1 405B runs at nearly a thousand tokens a second on Cerebras Inference, and took a quarter of a second to get the first token.

Tom’s Hardware · Nov 20, 2024

OpenAI execs mused over Cerebras acquisition in 2017 — to mitigate predicted Nvidia supply woes

To reduce reliance on Nvidia, OpenAI considered to take over Cerebras.

Tom’s Hardware · Nov 18, 2024

New AI Chip Leaves Nvidia, AMD, and Intel in the Dust with 20x Faster Speeds and Over 4 Trillion Transistors

This California-based startup recently unveiled Cerebras Inference, a cutting-edge solution reportedly up to 20 times faster than Nvidia (NVDA) GPUs, sparking attention across the tech landscape.

Barchart · Oct 28, 2024