STORY · PRODUKTER_
OpenAI reduces context window for Codex from 372k to 272k tokens
OpenAI has reduced the context window for its Codex model from 372k to 272k tokens. The change was made through a pull request and affects how much code the model can process simultaneously.
WHY IT MATTERS
A smaller context window means limited ability to handle larger code projects and can impact code generation quality. This suggests possible optimization for costs or performance, but represents a practical downgrade for developers.
SOURCES
MACHINE-GENERATED SUMMARY This summary is written by machine from the sources below. We sort and explain — but we are a way into the field, not the final word. Check the source when something matters to you.