New integrated mode for GPT-4 in ChatGPT+

[dmm]

They switched me to the new integrated mode. This is supposed to have all kinds of upgrades, in particular it is possible to read and write images in one session.

I still don't know if it is possible to competently edit images via this workflow (I'll try, and I'll read what other people say, but it might be difficult without a more image-oriented input system). Nevertheless, just like in dmm.dreamwidth.org/76698.html I read my avatar icon I am using here and talk to the new GPT-4 about it, and then I ask it to produce images based on that, see the comments for conversation and images.

Comments

[dmm]

It is still the case that "Sharing conversations with images is not yet supported"

So I am just copy-pasting it here.

ME: uploading my dreamwidth avatar and asking: "What is in this image?"

GPT-4:

The image appears to be a schematic representation of a physics concept. Specifically, it looks like a diagram of an optical system involving ray tracing through lenses or a lens system.

Here’s a breakdown of what the diagram might represent:

* There are two sets of parallel lines that could represent two lenses or a system with a lens and a mirror.

* The lines with arrows might depict light rays.

* The light rays are converging or diverging, indicating the focal points of the lenses or mirrors.

* The "f" symbols represent the focal length, the distance between the center of a lens or mirror and its focal point.

* The curved line with two arrows might represent a lens that is focusing the parallel light rays to a point, or it could indicate a curved mirror doing the same.

This kind of diagram is used in optics to illustrate how light behaves as it passes through or reflects off optical components. It’s a fundamental tool in designing and understanding optical systems like cameras, telescopes, microscopes, and eyeglasses.

ME: I like your interpretation! Actually, this is a neural machine, where single neurons are powerful enough to transform flexible tree-shaped tensors. Can you make an image creatively inspired by this?

[dmm]

Also, right now editing custom instructions is broken (one can't save the edited version or indicate whether to use it). Hopefully, the bug will go away on its own, but we'll see...

In any case, this is a massive, drastic upgrade, expect some things to get broken, some old workflow inventions to no longer work well and to be in the need of reinventing, etc.

[dmm]

Another interesting remark is that I don't have "f" in this image, but GPT-4 might have seen a version of this image containing "f" during pretraining, e.g.

https://clara.nytud.hu/~kk120/2017/bukatin/bukatin-4.png

[dmm]

OK, my version does not have the ability to read PDFs yet.

I started a new session, loaded my avatar image, and make the following straightforward request:

*****

Hi, I'd like to take this image and add a red ball to its upper right corner...

*****

This resulted in a stunningly beautiful image, which used the motifs from my request, but is completely different from what I asked for (so I am not hopeful about the ability to control image generation in this fashion):