Ember Vale 3D open-world action RPG
- Views
- 43.9K
- Likes
- 214
- Replies
- 28
- Saves
- 95
A comparison of 3D open-world action RPGs built from one prompt by Fable 5.5, GPT-6.2 Astra, Opus 5.5 and Fable 5.1, with the creator's rating of each.
Full prompt1,467 chars
Build a standalone playable 3D action RPG in the current folder: "Ember Vale", a small open-world fantasy valley you can explore and fight in. Initialize a git repo here. All code, file names and UI text in English. WORLD - One open valley: a village with houses and a well, a forest, a river with a bridge, ancient ruins on a hill, and a boss arena at the ruins. - Living details: grass and trees sway, smoke from chimneys, birds, fireflies at night, a full day-night cycle. PLAYER - Third-person hero with a sword. WASD to move, Shift to sprint, Space to dodge roll, left click to attack (3-hit combo), right click to block, 1–2 for spells (fireball, frost nova). - HP, stamina and mana bars. Hit reactions, knockback, damage numbers, a hit-stop on heavy hits. RPG - Enemies: wolves in the forest, skeletons at the ruins, each with simple AI (patrol, chase, attack, flee at low HP). - XP and level-ups, loot drops, an inventory with equippable sword and armor that change the hero's look. - One quest chain from a villager NPC with dialogue: clear the wolves → find the key in the ruins → defeat the boss. - Boss: a giant stone golem with 2 phases, a slam attack with a telegraphed shockwave, and a health bar at the top of the screen. - HUD: minimap, quest tracker, hotbar. LOOK - Stylized, polished, soft lighting with shadows, fog in the distance, glowing spell effects, particles on hits. - Camera: smooth third-person follow, drag to orbit, scroll to zoom.
Source: the creator's reply under the post. Kept in its original language, unedited.
Want more prompts like this one?
Get the 50 most-viewed Claude 5.5 video prompts on one page: the full original text, the creator and the post it came from. We'll only email you when there's a new prompt worth trying. Unsubscribe anytime.
Tools the creator mentioned
Original post: https://x.com/noclipepe/status/2117222592536789149
All works are open data at GitHub · awesome-opus-5.5-video.
Model attribution is as stated by the creator and was not independently reproduced. View counts are a snapshot from 2026-11-04. The work belongs to its creator; DM @GoSailGlobal on X for corrections or removal.
More comparisons
0:42AI self-portrait challenge: Sonnet 5.5 vs GPT-6 Astra
7.3M views
0:28Opus 5.5 vs GPT-6 Astra samurai game demo
1.1M views
0:13Gummy bear soft-body physics scene
631.5K views
0:30GPT-6 Astra vs Claude Opus 5.5 comparison
605K views
0:22Grok vs Opus grass-touching simulator cost test
554.9K views
0:44Opus 5.5 vs GPT-6 Sol Unreal game dev
544.2K views
Related articles
OpenAI Academy vs Anthropic: A Complete Comparison of Two Leading AI Companies' Free Learning Paths
Both of the top AI companies offer official free learning platforms — together that's 25+ courses and hundreds of hours of content, enough to take you from AI newcomer to resume-worthy engineer. This post maps out all 15 OpenAI Academy courses along a 10-week roadmap and provides a full side-by-side comparison with the Anthropic learning path.
Anthropic Claude Certified Architect Complete Roadmap: 8 Free Courses + $99 Exam
Anthropic launched the Claude Certified Architect certification on March 12, 2026, with 13 self-paced courses — all completely free, no registration required, no paywalls. The exam itself costs just $99. This post walks through a 12-week roadmap covering the 8 key courses in Weeks 1–9, with direct links to each.
OpenAI Agents SDK Major Upgrade: Harness and Sandbox Now Built Into the SDK — The Opposite Approach from Anthropic
OpenAI has shipped a major upgrade to its Agents SDK, with the headline changes being harness and sandbox support built directly into the SDK. Anthropic's Claude Agent SDK takes exactly the opposite approach — one gives you everything pre-assembled, the other hands you a toolbox.
DeepLearning.AI Complete Course Guide: 120 Courses, Taught by the Authors Themselves — 6 Goal-Based Learning Paths
DeepLearning.AI now has 120 courses — more than the previous eight major tech companies combined. What really sets it apart, though, is something no one else can offer: the courses are taught directly by the people who built the models and tools. This guide breaks down course selections across 6 goal-based learning paths.