Hacker Newsnew | past | comments | ask | show | jobs | submit | BlackRabbit1's commentslogin

A few weather forecast sites in Europe have them on their websites. It's just another forecast you can select and compare in an ensemble.

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.


> 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.


You could use this model as another input into the country-scale models.

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.


For hardware/electronics I also recommend looking at the CERN OHL licenses.

They cover a very specific niche GPL/AGPL/etc. do not cover properly.


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.


What kind of frequencies do these falcon trackers use? Any datasheets available?

Let us build FalconNogs (like Satnogs) with SDRs!


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)

For reviewing schematic/boards I recently developed something for internal tests:

1. A frontier model (either Opensource or closed source) gets a load of text to review a Kicad project systematically

2. The frontier model can extremely "ask" a cheap Gemini vision model to give it data from datasheets or specs.

Main problem: the quality dramatically hits the shitter done once it falls back to "pdf2latext" due to complex tables.

It was even able to do complex ngspice simulations. But you must offer it all datasheet PDFs.

$1-2 of tokens saved me from $70-80 bugged PCBs.


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.

Codex/Claude is much much much too expensive in relation to their limitations.

I stick to cheaper latest generation models on Openrouter (or EU-hosted providers when it comes to IP-protected stuff from work).


> Main problem: the quality dramatically hits the shitter done once it falls back to "pdf2latext" due to complex tables.

Could try screenshotting the PDF and passing that to gemini


This is what I'm doing by now. Uploading the entire .pdf dynamically then giving it a pipe to ask questions.

things are getting better - but the tooling required to make auto layout work are still hard

You mean that this helicopter hovering about my home is looking out for me?

Oh no, again

Can G3.7 use Google Maps for distance grounding?

Yep. It has access to much better route planning tools than the other models. The results are really good IME.

Sounds good!

I've been planing around with LLM-based trip planning for a very long time now as it fits my very ad hoc style of traveling very well.

But distances always had been.. lets say.. difficult.

Will test it with my upcoming trip to Greece then!


Not directly related to your embedded Go bug, but maybe helpful:

What really sky-rocketed my debugging skills in embedded devices was learning to utilize the Python plugin interface of 'gdb'.


I love it for hiking, walking in cities and driving a bicycle.

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.


Most don't want you to setup your own APN ;-)


That's a standard IoT usecase almost all telcos offer.

We have industrial SIMs with our own APN and get a IPSec tunnel to the Telco where we have a dedicated network to see our devices.


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!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: