Interactive jelly hammerhead shark
- Views
- 15K
- Likes
- 203
- Replies
- 23
- Saves
- 68
An interactive WebGPU soft-body jelly hammerhead shark, comparing Claude Opus 5.5 and GPT-6 Astra on the same prompt. Both versions are linked for viewing.
Full prompt1,792 chars
Make an interactive WebGPU soft-body study of a great hammerhead shark cast in two layers of jelly, resting on its belly in a soft photo studio. Build it from a signed distance field: an elliptical body section swept along the spine, slim at the neck, deep at the chest, with a slim caudal peduncle. Give it an oversized cephalofoil — a wide, flat hammer whose span is about 40% of the body length, with a nearly straight front edge, a small notch in the middle, ends swept slightly back, full and round at the front and thinning toward the back, with a large glossy eye at each tip. Seven kinds of fin from one recipe (convex leading edge, falcate trailing edge, thinning toward the tip): a very tall sickle-shaped first dorsal, second dorsal, pectorals, tall pelvic fins, anal fin and a lopsided tail with a subterminal notch. Clear tinted jelly over a milky white belly layer that also fills the underside of the hammer; trapped bubbles; a darker back, dusky fin tips, five gill slits, a small crescent mouth with milky teeth, grooves along the front of the hammer and pores beneath it, all drawn in the shader from rest-space coordinates so they stretch with the jelly. Simulate it as an XPBD tetrahedral mesh (snapped hex lattice, co-rotational elasticity, volume preservation, floor friction), with firmer fins. Muscle strain drives two moves: a slow head sweep from side to side, like a metal detector over the sand, and a tail swish. Let the user grab and stretch the jelly, twist with the scroll wheel or a second finger, drop beads of jelly bait, and switch between three colourways (steel, amber, gummy blue). Render with refraction, Beer–Lambert absorption, back-lit glow in the thin parts and tinted shadows. Show live mass, volume, fork length and the distance between the eyes.
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/vib3coded/status/2115402023935893904
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 2026-10-30. 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
630.4K views
0:30GPT-6 Astra vs Claude Opus 5.5 comparison
604.6K views
0:22Grok vs Opus grass-touching simulator cost test
554.3K views
0:44Opus 5.5 vs GPT-6 Sol Unreal game dev
543.6K 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.
My Current AI Tools List | 2025 Edition
The AI tools I shared at a corporate training session — if you can't be bothered sorting through options, just use the best ones.
The Complete Map of Free AI Learning: 10 Official Platforms, $0 Total Cost
Anthropic, OpenAI, Google, NVIDIA, Microsoft, AWS, Meta, IBM, DeepLearning.AI, Hugging Face — every official AI course from all 10 platforms is free. This is the master index: one comparison table + learning paths by role.
Using Manus with SimilarWeb Data for Competitor Research
Using Manus integrated with SimilarWeb data to research websites related to specific keywords and analyze their SEO and paid advertising strategies.