LLM took 45 minutes to model a dragon; a diffusion model did far better in 3
keenanisalive · x · 2026-10-10
Having Astra generate the dragon's 3D SDF model from the initial prompt took 45 minutes and 47 seconds and produced an, uh, beautiful result. The author notes it's amazing the LLM can do this at all, but it falls way short of what a diffusion model achieved in 3 minutes—still, he pushed on to see how far the approach could go.
More from coding & agent
- Alchemy + Cloudflare deploy praised as unbeatable feedback loop for agent dev — samgoodwin89 · 2026-10-10
- Over half of Vercel's deployments now start with coding agents; Supabase adds 1M databases a week — FinanceYF5 · 2026-10-10
- Learning math with ChatGPT as tutor: paper solving plus a scanning camera — generativist · 2026-10-10
- Dev Builds Robot Face Assembly Entirely with Codex, Awaits ESP32-S3 Shipment — kamathsblog · 2026-10-10
- Codex agent cold-contacts 290 businesses in 2 days, gets 14 onboarded — CtrlAltDwayne · 2026-10-10
- Midjourney starts testing its MCP with a limited creative community — midjourney · 2026-10-10