Hacker News Reader

How long? The cloud microparameterisation looks really exciting, but 10-year stability for a GCM (and "nearly conserving" water) is not great

I'm not sure. NVIDIA is also working on it (with, interestingly, some of the original AI2 folks).

Similar to the DeepMind effort, the ACE ML model that AI2+others developed is really just looking for parity with physical models at this stage. It looks like they've almost achieved this, with similar massive improvements in compute time + resource needs.

yep I just talked to one of the climsim guys and included the project in my writeup of this news:

https://techcrunch.com/2023/11/14/courtesy-of-ai-weather-for...

why is hiring phds a measure?

in this particular case, most of the important/needle-moving work being done in climate modeling is done with a hell of a lot of context about prior work. PhDs have that, by necessity.

They're also good at prioritizing outcomes, rather than other stuff.

if you don't hire phds you're not serious about it