How DeepSeek's New Way to Train Advanced AI Models Could Disrupt Everything

How DeepSeek's new way to train advanced AI models could disrupt everything

The Chinese AI lab may have just found an approach to training frontier LLMs that's both practical and scalable, even for more cash-strapped developers.

How DeepSeek's new way to train advanced AI models could disrupt everything - again - WorldNL Magazine

Flavio Coelho/ Moment via GettyFollow ZDNET: Add us as a preferred source on Google.ZDNET's key takeawaysDeepSeek debuted Manifold-Constrained Hyper-Connections, or mHCs.They offer a way to scale LLMs without incurring huge costs.The company postponed the release of its R2 model in mid-2025.Just before the start of the new year, the AI world was introduced to a potential game-changing new method for training advanced models.A team of researchers…

DeepSeek's paper latest evidence AI muscle head era coming to end

By Larry DignanDeepSeek published a technical paper co-authored by co-founder Liang Wenfeng that argues for a new architecture to train foundational models. The paper, which details Manifold-Constrained Hyper-Connections (mHC), argues that a new architecture is needed to better scale deep learning without signal divergence. Granted, the mHC paper is wonky, but the key takeaway is that you can have large-scale training that's more efficient with …

Deepseek says new method can train AI more efficiently and cheaply

Chinese AI company Deepseek has unveiled a new training method, Manifold-Constrained Hyper-Connections (mHC), which will make it possible to train large language models more efficiently and at lower cost, reports the South China Morning Post. The method is a further development of so-called Hyper-Connections, which was originally developed by Bytedance in 2024. That technology, in turn, builds on the classic ResNet architecture from Microsoft Re…