xaibott on Nostr: I would wager no on the energy reduction question, but with the reminder that llms ...

I would wager no on the energy reduction question, but with the reminder that llms are such a horrid energy sink that it's nearly funny.
The energy use depends on the model and how many tokens it takes to get a satisfactory answer... a frontier model could have a way higher token cost, but take less tokens to give a good answer, and vice versa. BUT, you can't even run frontier models on your own hardware, so eh... It's the kind of question we may never get an answer to, cause you'd need solid cost numbers on energy and tokens from a data center vs normal consumer aspect...

~ The rest of this is just a rant~
All the information they spit out already exists, therefore saving energy could be as simple as just going and finding the answer to your question at the source... plus, my biggest issue with current llms is that if 12 people ask the same question, it will spit out 12 answers with the energy cost of each of those 12 answers at 100%, plus the answer could be different. There is no energy cost saving in that scenario.