Muse Wonder Video Model Tested: 'Pretty Rough' Output, Every Narration in Australian Accent
danshipper · x · 2026-10-13
Dan Shipper tested the newly surfaced Muse Wonder video model by generating an explainer about personal benchmarks. Verdict: 'pretty rough.' Curiously, all its narrations come out in an Australian accent, which he hints may reveal something about its training data or origins — one of the first public hands-on tests of the rumored model.
More from Models
- Coinbase fine-tuned open Qwen3.5-9B on internal fraud data, beating Opus 4.5 by up to 35 recall points — sebpaquet · 2026-10-13
- Ethan Mollick: people take the Artificial Analysis Index and its scores way too seriously — emollick · 2026-10-13
- Meta to open-source Muse Spark weights soon, but Muse Wonder deemed too risky to release — MatthewBerman · 2026-10-13
- SubQ Launches Snap: 384K Multimodal Context, Beats Jev on Decision Index — alex_verem · 2026-10-13
- Meta's Alexandr Wang says natural communication was a big focus for Muse Wonder — alexandr_wang · 2026-10-13
- Dev says Opus 5.5 now feels sloppy and needs hand-holding like every other LLM — audrow · 2026-10-13