API Engine doesn't appear to be the one requested in some cases

[_j]

OpenAI is still capriciously injecting information into other API models, (which can also cause bad behavior). Demonstrated:

The model is not smarter - you are just treated as a poor API programmer that needs an AI model to answer this question.

Unwanted injection into new GPT-4o model system messages by OpenAI

A utility I’m working on reveals post-prompt added to the system message, working against proper operations. -- OpenAI context tester: gpt-4o-mini-2024-07-18 -- How many tokens input to send (min 8)? 18 max_tokens of response (0=unspecified)? 40 length for ints: 0 message contents: 14 tokens sending 18 tokens of input You are trained on data up to October 2023. You are trained on data up to October 2023. You are trained on data up to October 2023. You are trained on -- OpenAI context tester: g…

If you were to add capabilities of your own to the AI, this added message inserted by OpenAI into your system message can produce refusals instead of answering from your own new information.