> Problem is that the WN3 grid is still quite rough (5km) - but a that's a brutal improvement for many places compared to many other global models.
That's a pretty apples-and-oranges comparison. One would almost always use a high-resolution regional model if you needed certain details for different forecasting applications like renewable energy.
It's also worth noting that the 5km outputs are from a model decoder head that was trained against temperature and dewpoint at surface stations. According to the Rasp et al (2026) preprint, this head was designed for continuous sampling; the choice of a 5km grid is arbitrary. What we don't actually know is how well the model handles shocks like a frontal passage or impacts from things like outflow from storms - or even evaporative cooling from precipitation. We are limited to the output that DeepMind publishes; we can't run the model and stress test these things on our own.
That's all a long way to say that 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.
This would not likely be a great idea since you reduce your ability to understand inputs except for a few parameters. Explainable inputs become very important for many down the line processes used by government and industry alike, because said inputs and their predictive certainty can be quite informative, even critical, for accurate mesoscale prediction.
If model members were available, with all the usual measures, thats a fantastic place to start looking at serious inclusion. It doesnt seem thats the case, however.
I'd more bet that they are the critical infrastructure pillar everyone is scared to replace in a super important system, lol.
Maybe one of it saves the earth rotation control algorithm which the Earth Rotation Service requires for shooting their hidden ion cannons to keep it spinning.
We tested pretty much all available "AI" board and schematic auto-layouters in the market. All failed even with the most basic tasks.
On the other side the latest frontier models are pretty strong in writing embedded C + Assembler code and debugging it afterwards. It's fun to watch it writing crazy complex 'gdb' plugins in Python. This improved brutally.
I find it's (Sol at least, probably also Fable) great at writing Skidl schematics, evaluating PCB layout work and operating lab equipment while testing board (scope, psu, load, debugger)
Not sure why the complicated setup with Gemini. I assume you are on a Codex or Claude plan (100 or 200 EUR/USD/m). The model will just pull datasheets and use a combination of conversion to text and looking at bitmap renderings of the PDF. Haven't had that dramatic quality issue you mentioned. When the model isn't sure, it will just keep looking until it understands the datasheet clearly. But yes, it needs the datasheets.
Industrial 5G is super expensive. Also almost impossible to find a vendor that offers all the nice protocol features (Low Latency, native Ethernet tunneling, etc.) in their infrastructure.
We have about 20 client devices, I would very much prefer to throw a bunch of APs into the warehouse and it just works - DECT can do it, so wifi should, too. I'd settle for 10mbit/s!
Problem is that the WN3 grid is still quite rough (5km) - but a that's a brutal improvement for many places compared to many other global models.
Quite a few country-scale models go down to a 1-2km grid nowadays. This is very helpful in complex geography like mountains and alleys.
reply