
On the hardware side, the researchers built a high-power amplifier using a cascaded dual-gain-unit architecture and a multi-element doping design, achieving a maximum output of 33.5 dBm (roughly 2.24 W) while maintaining flat gain across the operating band. That higher-power, flatter amplification helped stretch an unrepeatered span without resorting to the remote-pumped amplifiers the team was trying to avoid. Because pushing that much power over a live optical link carries a real risk of failure, the system was wrapped in safeguards, including optical-path power anomaly detection, automatic interlock shutdown, and alarm-linked response mechanisms to catch faults before they damage equipment.
The stakes in this trial, and in HCF more broadly, tie directly to the AI buildout. As hyperscalers race to stand up ever-larger GPU clusters, the network linking those clusters, inside data centers and across the long-haul links between facilities, is fast becoming the bottleneck . HCF's lower latency lets operators site facilities farther from expensive, power-constrained hubs without a speed penalty, while its capacity headroom helps move the enormous traffic AI training and inference generate . The same properties make it attractive for latency-sensitive workloads like financial trading.
That promise is already pulling in serious money, mostly from the West. Microsoft , which moved early via its 2022 Lumenisity acquisition , struck manufacturing deals with Corning and Heraeus in September 2025 to scale production across Azure. AWS has developed its own HCF, claiming a 30% latency improvement over standard fiber, and says it wants more than it can currently get. Corning also has fiber deals with Microsoft, Meta, and Lumen, and is expanding in North Carolina with Nvidia's backing . Trials like YOFC’s are closing existing gaps toward full, widespread HCF deployment, though China's progress largely sits outside the Western supply chain now forming.
Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.
Etiido Uko is a news contributor for Tom's Hardware covering the latest updates in big tech and the PC industry. He is a mechanical engineer and senior technical writer with over nine years of experience in documentation and reporting. He is deeply passionate about all things engineering and technology, and is an expert in gadgets, manufacturing, robotics, automotive, and aerospace. ","collapsible":{"enabled":true,"maxHeight":250,"readMoreText":"Read more","readLessText":"Read less"}}), "https://slice.vanilla.futurecdn.net/13-4-24/js/authorBio.js"); } else { console.error('%c FTE ','background: #9306F9; color: #ffffff','no lazy slice hydration function available'); } Etiido Uko Social Links Navigation News Contributor Etiido Uko is a news contributor for Tom's Hardware covering the latest updates in big tech and the PC industry. He is a mechanical engineer and senior technical writer with over nine years of experience in documentation and reporting. He is deeply passionate about all things engineering and technology, and is an expert in gadgets, manufacturing, robotics, automotive, and aerospace.
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/networking/SPONSORED_LINK_URL
- https://www.tomshardware.com/networking/chinas-hollow-core-fiber-trial-pushes-51-3-tb-s-over-128-miles-without-signal-regeneration-milestone-targets-ai-era-networking-bottlenecks#main
- https://www.tomshardware.com/subscription
- Gigabyte Aero X16 gaming laptop delivers RTX 5060, 32GB RAM, and a 16-inch 165Hz 1600p display for 21% off
- Sony WH-1000XM5 active noise-canceling headphones for an all-time low $198 at Amazon — audiophile-grade audio and ANC for an affordable price
- AMD's new 10th Anniversary Ryzen 7 5800X3D CPU back in stock — Here's where to buy the revamped processor that's the fastest gaming chip available for AM4 platf
- How Businesses Are Building Specialized AI They Can Trust
- NVIDIA Powers Over 400 of the World’s 500 Fastest Supercomputers
Informational only. No financial advice. Do your own research.