GPT-5-Codex

Post by andybak » Mon, Sep 15, 2025, 9:53 PM UTC

Topfi wrote: post #9

One major improvement I have seen today, even before I saw the announcement, was that the model is far more reliable in using the Task Completion interface to communicate what stage of the prompt is being implemented. Previously this was only shown sparingly (especially in the first few weeks) and if, it didn't properly tick tasks, simply jumping from the first to completion at the end. Now this works very reliably a…

Post by andyferris » Mon, Sep 15, 2025, 10:02 PM UTC

inerte wrote: post #38

Oh since when Codex cli is now included as part of a ChatGPT plan? 99% sure that wasn't the case before. Time to try to use it for real.

Post by e1g » Mon, Sep 15, 2025, 10:35 PM UTC

bezzi wrote: post #44

is this model just super slow to anyone else?

Post by groby_b » Mon, Sep 15, 2025, 10:48 PM UTC

jumploops wrote: post #5

Interesting, the new model's prompt is ~half the size (10KB vs. 23KB) of the previous prompt[0][1]. SWE-bench performance is similar to normal gpt-5, so it seems the main delta with `gpt-5-codex` is on code refactors (via internal refactor benchmark 33.9% -> 51.3%). As someone who recently used Codex CLI (`gpt-5-high`) to do a relatively large refactor (multiple internal libs to dedicated packages), I kept running in…

Post by j45 » Mon, Sep 15, 2025, 10:55 PM UTC

jumploops wrote: post #5

Interesting, the new model's prompt is ~half the size (10KB vs. 23KB) of the previous prompt[0][1]. SWE-bench performance is similar to normal gpt-5, so it seems the main delta with `gpt-5-codex` is on code refactors (via internal refactor benchmark 33.9% -> 51.3%). As someone who recently used Codex CLI (`gpt-5-high`) to do a relatively large refactor (multiple internal libs to dedicated packages), I kept running in…