Four things about a context window decide what an agent does next: its size, whether the information in it is correct, whether information is missing, and the trajectory it is already on.

Added to korrents 15 Jul 2026 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. DHDex Horthy15 Jul 2026similar wording
• Every announcement of a longer context window hides the cost, which is that the model gets worse at following instructions. ASAravind Srinivas19 Jun 2024similar wording
• The point of context engineering is to do as much work as possible in the smart zone — roughly the first hundred thousand tokens of the context window. DHDex Horthy15 Jul 2026similar wording
• If you will write a huge markdown file so an agent has context, you should have written the documentation that gives a human the same context. KHKelsey Hightower3 Jun 2026similar wording
• An agent repeats its own history: whatever it did on the last change — ran the tests or skipped them — is what it will do on the next one, because it is predicting the next message in the conversation. DHDex Horthy15 Jul 2026similar wording

See this on the map →