agentic
agentic copied to clipboard
ChatGPT becoming less reliable
Verify latest release
- [X] I verified that the issue exists in the latest
chatgpt
release
Verify webapp is working
- [X] I verify that the ChatGPT webapp is working properly for this account.
Environment details
Node: 18 OS: Cent OS Stream 9
Describe the Bug
I think somehow the GPT is becoming stupid. I have not changed the prompt, but the response it generates is significantly shorter and less reliable than a few days earlier. I'm not sure if it is because the model had been changed or something else, but it did happen.