Skill-based 3D generation: 68k to 153k tokens but far more realistic leaves — skills set expectations, not teach
chaseleantj · x · 2026-09-13
Key numbers from the author's 3D scene generation test: with the same prompt, a one-shot run without a skill took 18 minutes and 68k output tokens; with a skill, 77 minutes and 153k tokens — but the leaves look far more realistic.
He explains the point of a skill today: it sets expectations rather than teaching the model how to do things — e.g. targeting Awwwards-level website quality, using the strongest appropriate rendering techniques. More on writing skills in future posts.
Related event: Setting expectations via skills key to better AI 3D generation(2 posts)→
More from coding & agent
- kalomaze: enough HuggingFace slop code exists that agents now copy it by default — kalomaze · 2026-09-13
- Stripe's Jeff Weinstein: agentic purchasing via Link got visibly better in a week — jeff_weinstein · 2026-09-13
- agent-skills launches a secure, validated skill registry for AI coding agents — tech-leads-club · 2026-09-13
- Stripe's agent wallet SDK sees fast adoption months after launch, says exec — jeff_weinstein · 2026-09-13
- Anthropic says engineers now ship 8x more code as AI nears recursive self-improvement — bibryam · 2026-09-13
- Non-programmer revives white-screened RetroFreak console using GPT-6 Astra in Codex — LordVitaly · 2026-09-13