This series of attempts to get Google’s Gemini model depict a horse riding an astronaut is great, as it is the article by Gary Marcus explaining why it is so hard to get an image generation model to do so. Similar to my experience trying to code with a foundation model, the last mile is really tedious and maybe subject to Zeno’s paradox.

Chat thread: gemini.google.com/share/7da… Gary Marcus’s article: garymarcus.substack.com/p/horse-r…