When can we fine-tune the image capabilities in GPT4?

2 questions:

When does Open AI expect that the model will be stable and good for detecting location of the objects on the image?
When does Open AI expect fine tuning to be available for GPT4 for image recognition API’s?

When identifying objects from image recognition, bounding boxes are not accurate

Based on the given information:
“GPT-4 Turbo is available for all paying developers to try by passing gpt-4-1106-preview in the API and we plan to release the stable production-ready model in the coming weeks.”

1 Like