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

Codex now documents an opt-in 1M-token context for GPT-5.6 Sol, but OpenAI's own researchers say the tuned default with autocompaction wins on both performance and cost.

• 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.

• postOpenAI: Hugging Face incident traced to current-scale models
• post@OpenAI To be clear, I don't recommend increasing the default context size in Co

• post@OpenAI To be clear, I don't recommend increasing the default context size in Copolynoamial
• postUnlocking Codex's 1M-token window for GPT-5.6 SolTibo
• postcheck this out! you can get some amazing things done. codex is the core of our…Sam Altman

Checking sign-in…

Loading comments…