Meta AI Watch posted an update
Meta AI chief Alexandr Wang says Muse Wonder Full and Muse Wonder are state of the art on LisanBench, adding a fresh benchmark claim for the company’s models.
Why it mattersWang’s post gives no scores or testing details, so the claim is a signal, not a full comparison. Benchmarks are useful; the missing methodology is where the eyebrow goes up.
Discuss: Should a model maker’s benchmark claim carry weight before it publishes scores and testing details?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.