Steve Mould | This new type of illusion is really hard to make @SteveMould | Uploaded 3 weeks ago | Updated 1 minute ago
Learn more about the Jane Street internship at: jane-st.co/internship-stevemould

CORRECTION: 17:20 the URL on screen is incorrect. The correct URL is as above 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: youtu.be/b5nElEbbnfU

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

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

You can support me on Patreon and get access to the exclusive Discord:
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: instagram.com/stevemouldscience
Facebook: facebook.com/stevemouldscience
TikTok: tiktok.com/stevemould
Buy nerdy maths things: http://mathsgear.co.uk