Context, not compute, will define the next generation of intelligence

For years, AI progress has been measured by scale: larger models, bigger datasets, longer context windows. Each new breakthrough promises that if we simply feed systems more data, we’ll get sharper insights.

Yet, at least outside of training, that assumption is running into trouble. As models absorb longer prompts, they often become less reliable. The model has more to choose from, which makes it more likely to focus on the wrong thing.

Researchers call this context rot: as an AI system processes more information, irrelevant details clutter its working memory. The result can be less accurate responses, higher costs, and a gradual erosion of trust.

A ...