not proud of it… man enough to say it
This is a AI post classified by Jev as Frontier models (a model release), kept by the AI Radar because it carries real work, not commentary.
not proud of it… man enough to say it after watching Claude Opus 5.5 just make this whole video + my tests over the last 12 hrs, it’s much better than I wanted to give it credit for some things you’ll notice: → you can get one 30 sec continuous shot and might have to do ZERO edits → it storyboarded, wrote, directed, produced, animated, and rendered a 1:1 high quality video in less than 20 mins (fckin nuts) → you can use Blender, but don’t have to. it wrote its own 3D renderer in Python lol (I practically gave it zero direction) → you also don’t need to use AI audio. ask it to grab real s
Posted by klöss (78.9k followers) 1 h ago · 16 likes · 2.2k views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- Same-day Official A, thinking off: Claude Opus 5.5 hits 151/157 (96.2%). GPT-6 Luna Pro… — @MichaelGannotti
- TP4 GLM 5.3 Flash has come alive. This thing is so smooth. — @TechMDAI
- this is what happens when you ask claude opus 5.5 to show you what’s inside its own mind. — @signulll
- That's more like it. — @teortaxesTex
- GLM 5.3 Flash TP 4 Bench - — @TechMDAI
- Claude Opus 5.5 vs Fable 5.1 vs GPT-Astra 6 — @ZentrixHQ
- Claude Opus 5.5 — @MiaAI_lab
- Claude Opus 5.5 drew self-portraits using JavaScript and composed the piano score. — @kevin_t_ngo
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 45.4k posts from 5k X accounts over the last 14 days, 1.9k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 23:05 UTC. Full method.