Culper Claims Cerebras Chips Fail Earlier Than Stated

Oct 29, 2026
Culper Research claims Cerebras wafer scale chips last 1.4 to 2.3 years, below the three to five years stated in draft IPO filings.
Culper Claims Cerebras Chips Fail Earlier Than Stated

Data Center Dynamics reports that Culper Research claims wafer scale chips from Cerebras Systems fail after 1.4 to 2.3 years. Draft IPO filings from Cerebras said its chips could last three to five years.

Culper, which disclosed a short position in Cerebras, claims the company did not solve thermal expansion problems at the hardware level. The firm alleges Cerebras uses constant dummy operations to manage the issue, leaving CS-2 systems at 70 percent of peak power while idle and CS-3 systems at 80 percent.

The report included customer statements describing systems that failed sooner than expected. Culper also claims the connector material used by Cerebras came from Paricon Technologies rather than being developed internally.

Cerebras shares fell 5.66 percent after the report and were down another 2.27 percent in premarket trading. Data Center Dynamics contacted Cerebras for comment.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief, AI Funding Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

AI Funding Brief

Guide
AI app builders

AI app builders

Tools that turn a description into a working web or mobile app, and the platforms companies use to build internal tools with AI

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.