An 11-minute billiards video hailed as the best intuitive explainer of LLM behavioral stability

ctjlewis · x · 2026-09-23

Developer @yusufknl recommends an 11-minute billiards chaos-simulation video as the best free explainer of why consistent LLM behavior is "a lucky island in a sea of chaos": GPT-5 doesn't actually behave the same way every time — each stable answer lives in a tiny stability zone, just like the winning zones mapped by bouncing balls off polygons. The video draws on 2007 chaos research on emergent stability, explaining why a single prompt tweak can drop an LLM into total gibberish.

Original post →

More from AGI Musings

AGI Musings channel →