This new type of illusion is really hard to make

Learn more about the Jane Street internship at: https://jane-st.co/internship-stevemould

Generative AI can be used to make images that look different in different orientations or different arrangements of parts.

Check out Matt's video here: https://youtu.be/b5nElEbbnfU

Check out the work of Ryan Burgert and colleagues: https://diffusionillusions.com
Check out the work of Daniel Geng and colleagues: https://dangeng.github.io/visual_anagrams/ https://dangeng.github.io/factorized_diffusion/

You can buy my books here:
https://stevemould.com/books

You can support me on Patreon and get access to the exclusive Discord:
https://www.patreon.com/stevemould

just like these amazing people:

Glenn Watson
Peter Turner
Joël van der Loo
Matthew Cocke
Mark Brouwer
Deneb

Twitter: http://twitter.com/moulds
Instagram: https://www.instagram.com/stevemouldscience/
Facebook: https://www.facebook.com/stevemouldscience/
TikTok: https://www.tiktok.com/stevemould
Buy nerdy maths things: http://mathsgear.co.uk