Grok 4.7 vs 4.6, but not another Three.js scene: one GLSL fragment shader, no libraries,…
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.
Grok 4.7 vs 4.6, but not another Three.js scene: one GLSL fragment shader, no libraries, no CDN. Pure math to pixels. Prompt: a planet from orbit, terrain, oceans, drifting clouds, day/night terminator with city lights, atmosphere at the limb, slow rotation, drag to tilt, a "Season" button that shifts the ice caps. Nothing to copy from a tutorial. Noise, lighting and atmosphere have to be composed correctly or it's mud. 4.6: 353 s · 23.1K tokens (17.7K thinking) · 12.4 KB 4.7: 723 s · 54.4K tokens (48.5K thinking) · 14.1 KB Both compiled first try, zero repairs. 4.7: sharper coastlines, vi
Posted by Wësche (2.9k followers) 1 h ago · 3 likes · 202 views · view the original post on X. Kept by the AI Radar as Frontier models.
More AI work like this
- MiniMax H3 Max by @fal takes the #1 spot on Video Editing by Design Arena with an Elo of… — @DesignArena
- 🎉 Congrats to @XiaomiMiMo on MiMo-V2.6: day-0 support in vLLM for both sizes. — @vllm_project
- Respect to Xiaomi for pacing the frontier using only 30 steps — @nrehiew_
- Grok 4.7 just made 4.6 look old. — @minchoi
- Grok 4.7 is behind only Anthropic models on AA-Briefcase, ranking just behind Opus 5 at… — @ArtificialAnlys
- Grok 4.7 update — @davidarngar
- Grok 4.7 has been released, so I tried out pagoda-garden. The harness is Grok Build. — @Hikari_07_jp
- SITUATION EXPLAINED: Is Jev a new kind of AI, or just a very fast classifier? — @MTSlive
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. 40.6k posts from 5k X accounts over the last 14 days, 1.7k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 00:02 UTC. Full method.