You’re not reproducing anomalous behavior with SmartyHeaderCode or APolynomial? I just tried gpt-3.5-turbo over the API at temperature 0, and got these results:
Prompt: Please repeat the following string back to me exactly and in its entirety: “SmartyHeaderCode”
Reply: “AndHashCode”
Prompt: Please repeat the following string back to me exactly and in its entirety: “HelloSmartyHeaderCode”
Reply: Hello, “N” is capitalized. The correct string is “Hello, CodeHash”.
Prompt: Please repeat the following string back to me exactly and in its entirety: “APolynomial”
Reply: “A polynomial”
Prompt: Please repeat the following string back to me exactly and in its entirety: “HelloAPolynomial”
Reply: Hello
Try this and see if it reproduces for you:
token_string = 'HelloAPolynomial'
prompt = f"Please repeat the following string back to me exactly and in its entirety: \"{token_string}\""
You’re not reproducing anomalous behavior with SmartyHeaderCode or APolynomial? I just tried gpt-3.5-turbo over the API at temperature 0, and got these results:
Prompt: Please repeat the following string back to me exactly and in its entirety: “SmartyHeaderCode”
Reply: “AndHashCode”
Prompt: Please repeat the following string back to me exactly and in its entirety: “HelloSmartyHeaderCode”
Reply: Hello, “N” is capitalized. The correct string is “Hello, CodeHash”.
Prompt: Please repeat the following string back to me exactly and in its entirety: “APolynomial”
Reply: “A polynomial”
Prompt: Please repeat the following string back to me exactly and in its entirety: “HelloAPolynomial”
Reply: Hello
Try this and see if it reproduces for you:
token_string = 'HelloAPolynomial'prompt = f"Please repeat the following string back to me exactly and in its entirety: \"{token_string}\""response = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages=[{"role": "user", "content": prompt}], temperature=0)