Mitchel Lensink

Photographer and writer working on long-term projects that uncover the overlooked beauty and quiet goodness in the world, shared in my monthly newsletter Dialogue.

The Netherlands
Closer #021 The image shared with ChatGPT as input.

To bring the 2025 series of Closer to a fruitful end, bestowed upon us is the opportunity to revisit its first editions. A newly release GPT-5 Prompting Guide breathes new life into our previously tried tests.

Closer
Closer #020 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

Crossing

A walk from one edge of a city to the other — west to east, north to south. A straight line through a place to see what connects its opposite sides.

Walking
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

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.