Ask HN: Codex is too slow. Is there any solution? 6 points by rule2025 1y ago ↗ HN The codex backend is of good quality, the frontend is average, but most importantly it is too slow. I wonder if OpenAI will improve it.
[–] esafak 1y ago ↗ Sonnet and Gemini are good and fast. Can't speak for Grok. [–] muzani 1y ago ↗ Grok Turbo is fast.
[–] moomoo11 1y ago ↗ It seems to work with less issues than CC opus.I don’t mind if it takes longer as long as the answer is correct more often.You can always be doing more work while one chat is working..
[–] naiv 1y ago ↗ the new 0.47 has a better performance now imho [–] i_have_an_idea 1y ago ↗ this seems like a crazy idea as the cli client has nothing to do with how many tokens per second the api streams
[–] i_have_an_idea 1y ago ↗ this seems like a crazy idea as the cli client has nothing to do with how many tokens per second the api streams
6 comments
[ 4.8 ms ] story [ 29.8 ms ] threadI don’t mind if it takes longer as long as the answer is correct more often.
You can always be doing more work while one chat is working..