"Do better!" prompting stalls fast; even top VLMs understand images unevenly
keenanisalive · x · 2026-10-10
The author found that generic "do better!" prompts stalled quickly, so he switched to giving human feedback instead. His experience: even the best VLMs understand images unevenly at best, especially for high-end 3D and image artifacts—making visual-feedback loops a bottleneck for refining LLM-generated 3D models.
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