I recently discovered a problem. Last week, I used gpt-5.2-codex xhigh to analyze and locate bugs in my game, fix game jitter, improve game fluency, and so on. The analysis by gpt-5.2-codex xhigh is extremely accurate, almost 100% capable of pinpointing the problem and achieving perfect repairs.
However, starting from the past few days, I have noticed that the speed of gpt-5.2-codex xhigh has become significantly faster during my use of codex5.2. Typically, it takes more than 10 attempts to locate the problem. On one occasion, I repeatedly tried to use gpt-5.2-codex xhigh to identify a bug that prevented characters from moving in the game, and it took me 10 attempts before finally locating the real bug. This is a serious waste of time. I would like to know if you have made any modifications to the model in the background or if it has become less intelligent.
You can contact me via email at [redacted].
We need an accurate codex, even if it takes a bit longer, we are willing to wait! I would like to know how I can use the previous accurate codex?
Please convey to the technical specialist that I previously used gpt-5.2-codex xhigh to fix a bug in my game code. The game code is programmed in C++, and when searching for a camera, the game interface shakes. gpt-5.2-codex xhigh can locate it 100% and fix it perfectly. However, in recent days, I have noticed that the response speed of gpt-5.2-codex xhigh seems to have increased. Today, I located a game where the mouse cannot control the movement of characters. My game used DX11 programming and DWM scheme, and finally found that the DWM scheme caused the characters in the game to not move. I searched repeatedly for 10 times, which seriously wasted time. Finally, the location was successful and fixed.
I want to know if there is a decline in intelligence now? I need the previous gpt-5.2-codex xhigh to be slow and precise more than fast!
Issues are reported via GitHub OpenAI Codex repository issues.
https://github.com/openai/codex/issues