Full-time AI video creator says he can no longer tell latest generated media apart
sven_ai · x · 2026-09-09
A creator who makes AI videos daily says combining ChatGPT-6 Astra's image generation with Seedance 2.5's video generation yields stunning results, and he no longer has confidence in distinguishing real from fake media. Note: the model names are unverified; this is a personal observation.
More from Multimodal
- Meta's MoEMB: MoE scaling beats 4x-larger embedders with just 3B active params — _reachsumit · 2026-09-09
- GPT Image 2.5 lands in Codex: image generation included in subscription, no API key needed — gabrielchua · 2026-09-09
- GPT-6 Astra turns 9 crappy studio photos into a fully interactive 3D model, demo stuns researchers — CSProfKGD · 2026-09-09
- Dev forks LichtFeld Studio and Colmap to optimize Insta360 dual-fisheye captures — janusch_patas · 2026-09-09
- LichtFeld Studio nightly now renders crisp distant mountains out of the box — janusch_patas · 2026-09-09
- HyperFrames hits #1 on GitHub as Claude Code-made launch video clocks 3M views in 2 days — toolstelegraph · 2026-09-09