I could probably train an AI that replicates that perfectly.
Yes, it could. And even after training its data can be manipulated to output whatever: https://www.anthropic.com/news/mapping-mind-language-model
I did it via ChatGPT for the irony.
There are lots of clues that this isn't happening (including the obvious upscaling call after the image is generated - but also the fact that the loading animation replays if you refresh the page - and also the fact that 4o claims it can't see any image tokens in its context window - it may not know much about itself but it can definitely see its own context).
https://openai.com/index/hello-gpt-4o/
Plenty was written about this at the time.
And to answer your question, it's very clearly in the linked article. Not sure how you could have read it and missed:
> With GPT‑4o, we trained a single new model end-to-end across text, vision, and audio, meaning that all inputs and outputs are processed by the same neural network. Because GPT‑4o is our first model combining all of these modalities, we are still just scratching the surface of exploring what the model can do and its limitations.
The 4o model itself is multi-modal, it no longer needs to call out to separate services, like the parent is saying.