> When toggled on, /fast mode in Codex delivers up to 1.5x faster token velocity with GPT‑5.4. It’s the same model and the same intelligence, just faster.
I hate these blog posts sometimes. Surely there's got to be some tradeoff. Or have we finally arrived at the world's first "free lunch"? Otherwise why not make /fast always active with no mention and no way to turn it off?
I hate these blog posts sometimes. Surely there's got to be some tradeoff. Or have we finally arrived at the world's first "free lunch"? Otherwise why not make /fast always active with no mention and no way to turn it off?