bdsqlsz's technical case against world models: more randomness and higher cost
bdsqlsz · x · 2026-11-08
bdsqlsz offers a technical argument: video models are essentially temporal causal diffusion models, and world models add spatial context on top, which brings higher randomness and higher cost.
More from Multimodal
- NVIDIA open-weights Nemotron 3.5 Transcribe: 30B-param speech model in 40 languages — dl_weekly · 2026-11-08
- Iridescent Prismatic Refraction: a reusable prompt template for spectral AI art — LudovicCreator · 2026-11-08
- SenseTime open-sources Code2Video: code-driven, editable AI video generation — AIwithGhotai · 2026-11-08
- MatAnyone-E cuts 4K video matting cost 13x, runs 28fps on an RTX 3090 — bdsqlsz · 2026-11-08
- Dev ships interruptible history podcast generator, 80% coded by Claude Code — Goldenchild123 · 2026-11-08
- SD community dev bdsqlsz: image models have hit their limit, next race is miniaturization — bdsqlsz · 2026-11-08