In 2023, I created a series of photographs exploring the possibilities of AI, called "The Most Likely Image".
Each image originated from a simple instruction. For most of the images I used something like: 
“contemplate the mystery of birth and death, while surrounded by scenes of civil war.”

The resulting images were rich with references to ‘classic’ photography, often echoing the styles of well-known photographers. Yet, due to glitches and imperfections in the software, they also felt uncanny—surprising, ambiguous, and at times unsettling.

Today, in 2026, it has become difficult to produce anything remotely interesting in this way. Most models now generate images that align closely with what one might expect from such a prompt: mysterious, atmospheric, and ultimately clichéd, filled with smoke, skulls, and a baby. Technically flawless, perhaps, but rarely thought-provoking. Three years ago, prompts functioned like seeds for hallucination; today, they operate like tools of art direction.

Still, I set out to recreate the original images using current software. The only method that seemed to work was to ask one chatbot to describe the original image in as much detail as possible, and then, crucially, to ask another chatbot to generate a new image based on that description.

The results look like perfect, flawless photos. Still, I’m not  sure what to make of them. Have a look..

Life and death 2026

01. birth and death 5 - original

02. birth and death 5 - 2026

03. birth and death 6

04. birth and death 17

05. birth and death 26 - 2026

06. birth and death 11

07. birth and death 9

08. birth and death 11-2

09. Devastated

10. birth and death 21

11. birth and death 24

12. birth and death 24-2

13. Devastated 3

14. birth and death 32

15.birth and death 41

16. disasonance 2

17. dissonance 9

18. birth and death 34

19. birth and death 39

20. Joy and Sorrow 9

21. birth and death 1961