Closer

A weekly newsletter where I take one of my photos, ask AI to describe it, then see what kind of image it can generate from its own description—an ongoing experiment in the capabilities of AI, and what that means for humans.

Closer #20 The image shared with ChatGPT as input.

GPT-5 is out and underwhelming. Our mini six-week experiment has come to an end. There's only five more regular editions of this newsletter before we wrap up with some preliminary conclusions in edition #25.

Closer
Closer #019 The image shared with ChatGPT as input.

GPT-5 is out! That's just in time for the last edition of our 6-week experiment using the same image. I'm curious to find out of this new model brings any improvements.

Closer
Closer #018 The image shared with ChatGPT as input.

The second-to-last edition of this experiment within an experiment, where AI gets to not only describe the image, and then generate an image based on said description, but also determine how to describe the image. Succes, finally?

Closer
Closer #017 The image shared with ChatGPT as input.

After this week, there's two more editions of the same image being described in different ways. Thankfully, because it's not bringing us anywhere. But that's interesting to note in itself too.

Closer
Closer #016 The image shared with ChatGPT as input.

We are sixteen weeks into this experiment, and I'm unsure if this is still providing value. This is the third week we let AI decide how to prompt and the results are... well, you be the judge.

Closer
Closer #015 The image shared with ChatGPT as input.

Week two of our 'experiment within an ongoing experiment' where AI is not only doing the image description and generation, but is also deciding the prompting to get to that description.

Closer
Closer #014 The image shared with ChatGPT as input.

Hey, so, thought: you know how we're already generating AI-images, based on AI-descriptions of real life images, right? What if... we also asked ChatGPT how to properly ask for those descriptions? Would that make it better?

Closer
Closer #012 The image shared with ChatGPT as input.

Imagine a cat behind a closed door, only paws and nose peeking from under the small crack between the door and the floor. Now imagine it again. How different are those results? Quite a lot, as it turns out.

Closer
Closer #011 The image shared with ChatGPT as input.

We all know things can get weird in AI image land. But what if you give it a weird image? Will we get twice the weirdness or will they balance each other out?

Closer
Closer #009 The image shared with ChatGPT as input.

Learning that it's the imperfections of our actions causing things to feel real is one of this week's biggest take-aways. And that's something I think we should ponder on for some time.

Closer

Subscribe to Dialogue

Become a member and get full access to my monthly newsletter 'Dialogue' about photography, walking and exploration, and my weekly newsletter 'Closer' about the role of AI in photography. For photographers, writers, artists, and explorers alike.

Oops! There was an error sending the email, please try again.

Awesome! Now check your inbox and click the link to confirm your subscription.