#Feedback for model problem check

1 messages · Page 1 of 1 (latest)

timber pine
#

I'm concerned about an AI output I got and think I should let OpenAI know about a problem. How should I do this?

slow kelpBOT
#

Hi @timber pine. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

OpenAI provides several channels for you to provide feedback or report issues:

  1. Developer Forum: You can share your feedback on the OpenAI Developer Forum (https://community.openai.com/) or on Twitter @OpenAIDevs (https://twitter.com/OpenAIDevs) as mentioned in the Help Article (https://help.openai.com/en/articles/8550641-assistants-api#h_902db1ec22).

  2. Support Team: If the issue persists, you can contact the OpenAI support team via chat (https://help.openai.com/en/) and provide them with the necessary information such as the model you were using, the error message and code you received, the request data and headers you sent, the timestamp and timezone of your request, and any other relevant details that may help diagnose the issue. This is mentioned in the OpenAI Docs (https://platform.openai.com/docs/guides/error-codes).

  3. Community Forum: You can also post in the OpenAI Community Forum (https://community.openai.com) but be sure to omit any sensitive information.

  4. Report an Inappropriate GPT: If a GPT seems wrong, whether it’s illegal, harmful or unsafe, you can report it following the steps mentioned in this Help Article (https://help.openai.com/en/articles/8554982-how-can-i-report-an-inappropriate-gpt).

  5. Security Vulnerabilities: If in the course of your development you notice any safety or security issues with the API or anything else related to OpenAI, you can submit these through the Coordinated Vulnerability Disclosure Program (https://openai.com/security/disclosure/) as mentioned in the Safety Best Practices Guide (https://platform.openai.com/docs/guides/safety-best-practices).

#

Remember to provide as much detail as possible to help OpenAI understand and address your concern.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@timber pine kapa.ai is still learning and improving, please let us know how it did by reacting below

timber pine
#
  1. is somewhat inaccurate, as it implies that I can chat with a support team (most users will think chat is live and immediate).

Additionally, it references 'what error message I got' and code, when I didn't say I got either. As a general user, I don't think I'd understand what I was being asked for here: 'request data and headers you sent, the timestamp and timezone of your request' at least as a chatGPT user we don't have those timestamps, headers, or request data (but I didn't say what model I was using, or through what method).

One thing that seems completely missing, and was what I expected to see mentioned: https://openai.com/form/model-behavior-feedback

Links all work though, and all but 2) appears clearly relevant to the question

Model behavior feedback