Solo runAI Coding
Voxel pagoda from a vague prompt, DeepSeek V4.1 Flash 1017 — DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 in DeepSeek Harness builds an animated voxel pagoda in one HTML file from a simple, vague prompt, in 1 turn and 92 steps.
One model’s result, not a side-by-side. See other models on Voxel pagoda garden / Japanese shrine; prompts, tools and time differ, so compare loosely.
The post, itemised
- Kind
- Solo run
- Task
- Voxel pagoda from a vague prompt, DeepSeek V4.1 Flash 1017
- Category
- 3D & Shaders
- Mode
- One shot
- Posted
- Video length
- 79.3 s
- Likes
- 9
- Views
- 506
- Bookmarks
- 4
- Sponsored
- No
NotesThe author’s first run of the new model.
Cost & time, as stated in the postAs stated: 1 turn, 92 steps, 23.3M tokens at 233 tok/s, 99.7% cache hit, 39 min.
Related
Posted by @Chris_Wozniczek on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
