> Yes, you can send me an image as long as it's in a supported format such as JPEG, PNG, or GIF. Please note that as an AI language model, I am not able to visually process images like a human would. However, I can still provide guidance or advice on the content of the image or answer any questions you might have related to it.
Fair, but if it can analyze linked image, I would expect it to be able to tell me what text is present in the image. That seems useful and well-within the capabilities of their connected image models.
> I apologize for the confusion. Can you please provide me with the correct image or link to the design so that I can provide an accurate answer to your question?
It claims to understand how to look at images, but it failing miserably when I give it a simple sign-up modal Figma. I ask it what text/copy is in the design, which it claims to be able to answer, but it hallucinates a navigation bar, a logo, and other generic things that are simply not present in the design. It gets the copy all wrong. Once, it said that my design was a Celtic knot. Once I told it that it was a sign-up modal, it started spitting out generic sign-up modal React code that had absolutely no basis in the presented design. I tried engineering the prompt quite a bit, telling it that it was wrong, and needed to focus on the design at hand rather than generic designs it knows about, but with no success.
ChatGPT was confidently incorrect here which is unfortunate. I wish ChatGPT truly hooked into an image processing model, but it seems like it doesn't. Oh well. I guess I'm just going to have to write this code myself... :)
Fair, but if it can analyze linked image, I would expect it to be able to tell me what text is present in the image. That seems useful and well-within the capabilities of their connected image models.
> I apologize for the confusion. Can you please provide me with the correct image or link to the design so that I can provide an accurate answer to your question?
It claims to understand how to look at images, but it failing miserably when I give it a simple sign-up modal Figma. I ask it what text/copy is in the design, which it claims to be able to answer, but it hallucinates a navigation bar, a logo, and other generic things that are simply not present in the design. It gets the copy all wrong. Once, it said that my design was a Celtic knot. Once I told it that it was a sign-up modal, it started spitting out generic sign-up modal React code that had absolutely no basis in the presented design. I tried engineering the prompt quite a bit, telling it that it was wrong, and needed to focus on the design at hand rather than generic designs it knows about, but with no success.
ChatGPT was confidently incorrect here which is unfortunate. I wish ChatGPT truly hooked into an image processing model, but it seems like it doesn't. Oh well. I guess I'm just going to have to write this code myself... :)