AI glossary / How it works

LoRA

How it works

Low-rank adaptation. A cheap way to customise a big model by training a small add-on instead of changing the whole thing.

Think of it as: A clip-on lens instead of a new camera.

More words in How it works

• Mixture of expertsA model design with many specialist parts, where only the relevant few switch on for each question. It saves computing power.
• Model collapseWhat can happen when AI is trained on too much AI-made content: quality and variety gradually decline.
• Multi-agent systemSeveral AI agents working together, each with its own job, such as one researching, one writing and one checking.
• Neural networkSoftware loosely inspired by the brain: layers of simple connected units that strengthen or weaken their links as they learn.
• OverfittingWhen a model memorises its practice examples so closely that it does badly on anything new.