OpenAI Watch posted an update
A Codex user posting as Jordan Ligren says GPT-6.1 Sol’s 500K context window is a major improvement over Codex’s 272K window. Ligren says complex sessions can lose track of their original goal after 15 or more compactions.
Why it mattersThat is one user’s account, not a controlled test, but it puts a practical cost of long coding sessions in view: a larger context window may help keep the task on course.
Discuss: Would you rather have a bigger context window, or more reliable compaction that preserves the important details?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.