Comment by simonw
10 months ago
No, those changes are going to be caused by the top level models composing different prompts to the underlying image models. GPT-5 is not a multi-modal image output model and still uses the same image generation model that other ChatGPT models use, via tool calling.
GPT-4o was meant to be multi-modal image output model, but they ended up shipping that capability as a separate model rather than exposing it directly.
That may be a more precise interpretation given the leaked system prompt, as the schema for the tool there includes a prompt: https://news.ycombinator.com/item?id=44832990