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.
More from AGI Musings
- Dustin Moskovitz: the single largest funder of the EA ecosystem, with billions to AI safety — SydSteyerhart · 2026-09-23
- Open-source advocates call doom narratives a regulatory moat against open weights — AlexTensor · 2026-09-23
- When AI science bifurcates from human science, like math seems set to do — burny_tech · 2026-09-23
- Show today's LLMs to experts 10 years ago and they'd call it AGI — JacksonKernion · 2026-09-23
- Benedict Evans: AI may automate much of junior lawyers' and consultants' routine work — rohanpaul_ai · 2026-09-23
- AI safety will follow engineering tradition: formal proofs for simple cases, evals for complex — burny_tech · 2026-09-23