One global function takes LLM-evolved level generation from ~0% to ~100% playability
Amidos2006 · x · 2026-09-09
Key result: having at least one global function changes everything — all problems except Binary need at least 1 global function for high playability (Zelda: 0% with 0 globals, 100% with 1). Method: code represented as Python, Claude Opus 4.8 as generator, prompted to follow function signatures and produce new useful functions; fitness is cascaded — 100% playable levels before diversity counts.
More from coding & agent
- GRID launches Auto-Engineering: agents build robot skills, first skill in ~4 hours — akapoor_av8r · 2026-09-10
- Context as a control surface: steering agentic runs via MCP over stdio — mostly_deterministic · 2026-09-10
- Firecrawl adds pay-as-you-go to paid plans with $5 auto top-ups and spending caps — devdigest · 2026-09-10
- Google ships ADK for Kotlin 1.0 with multiplatform core and compile-time tool schemas — fhinkel · 2026-09-10
- Google Launches Data Agent Kit for In-IDE Data Workflows — rseroter · 2026-09-10
- Launched 30 agents overnight, Windows Update restarted the machine an hour later — kevinnbass · 2026-09-10