These models actually outperform traditional methods on many fronts, including accuracy a lot of the time. They are technically generative AI models, but they're definitely not LLMs.
Really exciting to see NOAA finally make some progress on this front, but the AIGFS suite likely won't outperform ECMWF's AIFS suite any time soon. The underlying architecture between AIFS and GraphCast/AIGFS is pretty similar (both GNNs), so there won't likely be a model-level improvement. And most of ECMWF's edge lies in its superior 4DVar data assimilation process. AIGFS is still being initialized on NOAA's hybrid 4DEnVar assimilation process as far as I understand it, which is still not as good as straight up 4DVar unfortunately.
Things are changing quickly in this area. Several projects/companies working on AI data assimilation (an alternative route to creating analysis data like ERA5)[0].
Also a lot of companies working on the data collection side, replacing/augmenting government data collection. Spire's an example of this in the space domain, and Windborne and Sorcerer (my company) do weather balloons.
SumUp | Technical Lead | ONSITE or REMOTE (Boulder, CO)
SumUp is a fintech company focused on empowering small businesses. We're primarily focused on enabling merchants to accept payments, and we build a number of tools including POS devices (similar to Square). As a company we've primarily operated in European markets and Brazil, but we're hiring in the US to build out our Global Expansion team which will be responsible for establishing new markets including the United States.
We're looking for experienced engineers with a history of technical leadership on big projects. We use tools like Elixir, Ruby, Golang, (among others) to work on a myriad of technical projects related to establishing new markets.
We're especially interested in engineers who have experience with hardware certification and payments infrastructure, and those who have experience working on open source projects.
Send me an email at [email protected] and mention hackernews if you're interested.