Grok 4.7 tested: HTML water glass and procedural watch exploded views impress
Daniel_Farinax · x · 2026-09-22
Developer DanielFarinax shared more Grok 4.7 tests: after building a running exploded view of a procedurally generated watch from scratch, he made a glass of water in HTML, generating the background and countertop images via Imagine. Observation: the model needs more prompting than usual to get going, but is fully capable of these complex visualizations.
More from Models
- Unverified DataBench Charts Fuel Rumors of OpenAI's Internal Model 'Luna' Ahead of GPT-6 — almmaasoglu · 2026-09-22
- TypeSafe CEO on Jev: machine-native models for code, RLCD over RLHF — Latent Space · 2026-09-22
- Mimo 2.6 Pro hands-on: needs more steering, rivals top models after corrections — power97992 · 2026-09-22
- OpenAI's 24-day-old internal model reportedly solved 100+ open math problems — IgorCarron · 2026-09-22
- Paradigm unveils Limite 1B 'Violetto', a 1B model built for high-frequency mathematical intelligence — tensorqt · 2026-09-22
- Speculation: Grok Pro line is an extension of Flash line, mxfp4 QAT likely speeds RL rollouts — stochasticchasm · 2026-09-22