Getting LLMs to simulate “true” randomness or generate diverse outputs is surprisingly difficult. We found a simple prompting trick that solves this by having the model generate and manipulate a random string. To be presented at #ICLR2026 this week!

Blog: https://t.co/CyevqqJ5ej https://t.co/dN0yZZ5Mij

— hardmaru (@hardmaru) 20 avril 2026

Getting LLMs to simulate “true” randomness or generate diverse outputs is surprisingly difficult. We found a simple prompting trick that solves this by having the model generate and manipulate a random string. To be presented at #ICLR2026 this week! Blog: https://
pub.sakana.ai/ssot

→ View original post on X — @hardmaru