I'm wondering, is there a tool or something out there that helps me pick a model, in the vast sea of models out there these days? Every time I need a model for something I see the list on openrouter and I'm completely overwhelmed.
I'd love to be able to explain my use case, my cost preferences and have a tool select a few good models to try.
E.g. I wrote a tool that cleans out my email spam box. It classifies emails that are already flagged as spam, and if it's very obviously spam it removes it permanently (keeps a copy on disk though). And after x emails, it goes through the list of deleted spam mails and suggests email rules. What model would be best suited? I'd love to be able to explain this use case and get this info served to me. The list of models and the information about what they're good at is just too splintered and spread out. I landed on google/gemma-4-31b for now, because it's cheap and good enough and also supports Dutch and French a bit. But I can't realistically try them all.
I doubted this but it does look like there's an actual government initiative that mandates 80% clean energy for all new data-center builds: <a href="https://www.fastcompany.com/91578780/how-china-is-powering-new-data-centers-with-clean-energy" rel="nofollow">https://www.fastcompany.com/91578780/how-china-is-powering-n...
that said, China is also rapidly scaling up coal-fired plants: <a href="https://apnews.com/article/china-coal-power-plant-carbon-climate-change-ba86e7584e3afe1826eed5cffa25354a" rel="nofollow">https://apnews.com/article/china-coal-power-plant-carbon-cli...
those presumably support all of the surrounding infrastructure + people + manufacturing so it's not as if it's truly solar-powered. but it's still handily better than the state-by-state abandonment of clean energy goals here in the US - I lay this out a bit here: <a href="https://news.ycombinator.com/item?id=49700743">https://news.ycombinator.com/item?id=49700743
Note that the 80% are qualified with "inside eight large data center hubs created in China’s “East West Computing Strategy”." Most new data centers are built elsewhere and will use whatever source of energy is most convenient.
>80% are qualified with "inside eight large data center hubs created in China’s “East West Computing Strategy”." Most new data centers are built elsewhere
this is a pedantic misinterpretation of the scope of East Data, West Computing. the hubs are all in tier one cities with the power generation capacity to handle them. each hub is comprised of dozens of data-centers and are the place to build because of large economic incentives, infra guarantees, and university-trained talent living in close proximity
see <a href="https://www.sciencedirect.com/science/article/pii/S2095809924005058" rel="nofollow">https://www.sciencedirect.com/science/article/pii/S209580992...
>This initiative is expected to accommodate up to 95% of China’s digital data needs through this reorganization
>Within a year of implementation, more than 112 new data centers have either been authorized, under construction, or completed across the planned computing hubs
this project itself is the thing that has all the other nation states in the world clutching pearls about not supporting their native AI corporations enough. it's something you and everyone else should really familiarize yourself with because it is one of the major items influencing current realpolitik and economic decisions (and is likely going to be the thing that'll lead us to a thrice-in-a-lifetime sized recession but that's a convo for a different day)
mavamaarten · · focus · HN ↗
I'd love to be able to explain my use case, my cost preferences and have a tool select a few good models to try.
E.g. I wrote a tool that cleans out my email spam box. It classifies emails that are already flagged as spam, and if it's very obviously spam it removes it permanently (keeps a copy on disk though). And after x emails, it goes through the list of deleted spam mails and suggests email rules. What model would be best suited? I'd love to be able to explain this use case and get this info served to me. The list of models and the information about what they're good at is just too splintered and spread out. I landed on google/gemma-4-31b for now, because it's cheap and good enough and also supports Dutch and French a bit. But I can't realistically try them all.
rudicjd2747 · · focus · HN ↗
paimapi · · focus · HN ↗
that said, China is also rapidly scaling up coal-fired plants: <a href="https://apnews.com/article/china-coal-power-plant-carbon-climate-change-ba86e7584e3afe1826eed5cffa25354a" rel="nofollow">https://apnews.com/article/china-coal-power-plant-carbon-cli...
those presumably support all of the surrounding infrastructure + people + manufacturing so it's not as if it's truly solar-powered. but it's still handily better than the state-by-state abandonment of clean energy goals here in the US - I lay this out a bit here: <a href="https://news.ycombinator.com/item?id=49700743">https://news.ycombinator.com/item?id=49700743
yorwba · · focus · HN ↗
paimapi · · focus · HN ↗
this is a pedantic misinterpretation of the scope of East Data, West Computing. the hubs are all in tier one cities with the power generation capacity to handle them. each hub is comprised of dozens of data-centers and are the place to build because of large economic incentives, infra guarantees, and university-trained talent living in close proximity
see <a href="https://www.sciencedirect.com/science/article/pii/S2095809924005058" rel="nofollow">https://www.sciencedirect.com/science/article/pii/S209580992...
>This initiative is expected to accommodate up to 95% of China’s digital data needs through this reorganization
>Within a year of implementation, more than 112 new data centers have either been authorized, under construction, or completed across the planned computing hubs
this project itself is the thing that has all the other nation states in the world clutching pearls about not supporting their native AI corporations enough. it's something you and everyone else should really familiarize yourself with because it is one of the major items influencing current realpolitik and economic decisions (and is likely going to be the thing that'll lead us to a thrice-in-a-lifetime sized recession but that's a convo for a different day)