Encoding human layer-by-layer cube strategy for a decision-making AI
gdechichi · x · 2026-09-22
gdechichi explains the setup: computers have solved Rubik's cubes for years via graph search, unlike humans who solve layer-by-layer in steps of 4-20 moves. He encoded those instructions to see if decision-making AI Jev could make the right calls—and it solved the cube like a human.
Related event: Dev Tests Decision AI 'Jev' Solving a Rubik's Cube Like a Human(5 posts)→
More from Fun
- 50+ NeurIPS 2025 papers found containing AI hallucinations that slipped past peer review — CSProfKGD · 2026-11-12
- 'Just Train on Test': The Benchmark-Gaming Joke AI Circles Keep Making — pranjalssh · 2026-11-12
- The 2026 Developer Slack: 'My Claude Says to Tell Your Claude It Is Sorry' — jmugan · 2026-11-12
- Show HN: Papers, Please remake casts you as a YC partner vetting startups — bolau · 2026-11-12
- Meme: "AIs are mysterious aliens we grow" vs "just switch to a different ontology" — sebkrier · 2026-11-12
- Gemini 4 Carbon builds a full 3D aquarium in Blender and Three.js in ~6 hours — sunjiao123sun_ · 2026-11-12