Intel / post

Autocompaction in Codex is really good. @OpenAI recognized early on that it woul

Context

OpenAI's Codex manages a growing conversation by replacing older input with a smaller representation, freeing room for continued work. Its engineering explanation describes this automatic . Noam Brown praised the behavior while pointing to an optional million- configuration. The configuration explanation he quoted says a larger window retains more code, tool output and history before compaction. His separate recommendation was to keep the default size.

Terms in this piece · Glossary

context compaction — Summarizing an agent's earlier conversation to free room in the context window so a long session can keep going.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.