1. Demo accessibility and UI confusion
Several users struggled to find or load the interactive demo, citing broken links, 404 errors, and unclear button labels.
- ssl‑3: “I'm not seeing that kind of demo. I just see a video, a bunch of future‑tense words about what could be done by someone, and the requisite hype.”
- tidbeck: “After signing in I get a 404.”
- zamadatix clarified the two “Explore Weather Lab” buttons, noting one leads to a pre‑made dashboard while the other lets users try the API themselves.
2. Forecast accuracy and real‑world usefulness
Opinions split on whether the new model improves practical weather prediction, with many comparing it unfavorably to Dark Sky and citing frequent errors.
- bastawhiz: “It's great that they're working on this, but I am puzzled at how absolutely awful the forecasts are in the Google weather app for my area…. I guesstimate that it has less than 50% accuracy for my area.”
- hankbond: “Having more reliable weather predictions is a genuinely useful product.”
- gonzalohm & timmg: Both reported switching to Windy due to perceived poor accuracy (<50%) in their locales.
3. Technical assessment of model capabilities
Discussion focused on the model’s resolution, ensemble nature, and how it compares to traditional NWP and regional models.
- counters: “Problem is that the WN3 grid is still quite rough (5km)… the 5km resolution is (a) limited to temperature fields, and (b) we don't know if the 'additional' resolution has any impact whatsoever on the phenomena that one would typically use a mesoscale‑resolving forecast for.”
- BlackRabbit1: “WN3 grid is still quite rough (5km) – but that's a brutal improvement for many places compared to many other global models.”
- RockstarSprain: Questioned iOS availability, noting Google Search and Maps currently show only basic information.