Configured for GPT-4 but responding as GPT-3

[3gyptian]

Verify it's not a duplicate bug report

• I searched for similar bugs reported on GitHub and nobody has reported a similar issue. Search all issuees.
• I read Troubleshooting guide on Readme and there is not a guide on how to solve my problem.

Describe the Bug

When I ask on the prompt: Are you based on GPT-3 or GPT-4 architecture?

It returns: I am based on the GPT-3 model.

When running python script using the same API key and question it returns: We are based on GPT-4 architecture.

I confirmed that Genie AI settings are set to gpt-4. Is there something else that needs to be configured?

thank you!

Please tell us if you have customized any of the extension settings or whether you are using the defaults.

defaults but with gpt-4 setting

Additional context

No response

[3gyptian]

So I ran the same python script testing the API the following morning and it returned GPT-3 ! Looked into it some more andit turns out the response can very arbitrarily even when connected to GPT-4.

Here's the updated python script that properly returns the gpt model one is connected to:

import openai

openai.api_key = '<api key>'

response = openai.ChatCompletion.create(
  model="gpt-4", # You can adjust this to the specific GPT-4 chat model ID you have access to.
  messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Are you based on GPT-4 architecture?"}
    ]
)

print("Model used:", response['model'])
print("Response:", response['choices'][0]['message']['content'].strip())

Which outputs:

Model used: gpt-4-0613
Response: As an artificial intelligence, I'm a model powered by OpenAI's GPT-3. At the moment, a GPT-4 model hasn't been released. Please note that even while using the GPT-3 model, I'm continuously updated to improve my capabilities and provide better assistance.

Go figure .. lol

Closing this bug ..

[3gyptian]

closed