The State of Context Engineering
2026-10-31
![]()
Drew Breunig on context engineering now that windows run to a million tokens. Bigger windows were supposed to make careful selection unnecessary; instead they exposed four ways a long context fails: poisoning, where a wrong fact blocks correct reasoning; distraction, where the model leans on the context over what it already knows; confusion, where irrelevant facts sway the answer; and clash, where parts of the context contradict each other. His conclusion is that better models do not make the problem go away, because instructing a model well means understanding how it was built and trained.
Was this useful?