Scientists say they have solved a major AI bottleneck – now they can process calculations “at the speed of light.”

Scientists have developed a fundamental architecture for next-generation optical computing – using light instead of electricity to power chips – that could revolutionize how things work artificial intelligence (AI) models are trained and executed.

At the heart of large language models (LLMs) and those based on deep learning is a weighted organizational structure called a “tensor,” which functions like a filing cabinet with sticky notes indicating which drawers are used most often.

When an AI model is trained to perform a task or function, such as recognizing an image or predicting a text string, it sorts the data into these tensors. In modern AI systems, the speed at which models can process tensor data – or search through filing cabinets – is a fundamental performance bottleneck, placing a hard limit on how large a model can become.

In typical light-based computing, models analyze tensors by firing laser arrays multiple times. They work like a machine that…