Same-prompt test: fable 5.1 vs sol 5.6 generating a realistic three.js waterfall
majidmanzarpour · x · 2026-09-03
Developer majidmanzarpour ran an identical prompt — a single-file, maximum-realism three.js waterfall — through two AI coding models, fable 5.1 (xhigh) and sol 5.6 (max), sharing video of the side-by-side results plus the full prompt for reproduction.
Related event: Same three.js waterfall prompt pits fable 5.1 against sol 5.6(2 posts)→
More from coding & agent
- Google Cloud launches free hands-on training to build and ship production agents — leslysandra · 2026-09-03
- Memoryfields: agent memory as portable Markdown files plus an optional SQLite index — rseroter · 2026-09-03
- WHALE Paper: Alternating Weight and Agent Harness Optimization Gains Up to 24 Points — Kangwook_Lee · 2026-09-03
- 10-year brand designer shares full workflow to build a brand system from 1 reference image — charis_ai · 2026-09-03
- Anthropic open-sources Claude Commerce Agents blueprint across retail, travel, telecom — ClaudeDevs · 2026-09-03
- Claude launches commerce agents blueprint; Shopify and Priceline already on board — ClaudeDevs · 2026-09-03