Context engineering: managing 1M-token windows without context rot — companion videos

Chroma

Kelly Hong walking through Chroma's research on 18 models — why needle-in-haystack scores are misleading, how performance degrades with ambiguity and distractors, why even simple string-repetition tasks degrade past 500 tokens. Short, evidence-based, and exactly the case the article needs you to take seriously before getting to the engineering moves.

What you should get from this: Understand how long context can fail under ambiguity and distractors, then design tests around that risk.

Watch or know first: None beyond basic LLM vocabulary — it's a short research talk.

LangChain

Lance Martin's framework — write, select, compress, isolate — with concrete examples of when to summarise an action history, when to offload state to files, and when to spin up sub-agents purely to protect the parent's context. Maps almost directly onto the article's section on managing 1M-token windows in practice.

What you should get from this: Apply write, select, compress and isolate patterns to manage agent context deliberately.

Watch or know first: Experience building or operating agents with long-running context.