Originally published at getunblocked.com on August 10, 2026.
Context rot is the gradual degradation of an LLM's output quality as its context grows — the model starts missing, misreading, or ignoring information that is still right there in the window. It sets in long before the window is full, and it is the usual reason an agent that felt sharp for the first hour starts fumbling in the second. Nothing broke, and no data was lost. The model is simply using its own context worse than it did at the start of the session.
TL;DR: An LLM's output quality decays as its context window fills, even though the information it needs is still present in the window. The cause is a finite attention budget, not finite memory: every token in the window competes for the model's attention. The fix is to curate what enters the context instead of enlarging the window.
What is context rot?
Context rot is the decline in a model's ability to accurately use information already sitting in its context window as the token count grows. Instructions get dropped and recall turns fuzzy even though every relevant token remains technically available to the model.
