Comment by Aboutplants
13 hours ago
I tend to think this will end up being a good thing. It will force people to actually think about the best use cases and utilization of tokens while others will push to optimize models and tools to improve cost and efficiency. “Life finds a way”
I think it will be a good thing for other reasons: there will be a massive push to get hardware good enough to run local LLMs burning infinite tokens.
Yeah but energy is still a cost, and local inference without batch and multiplexing for many users (like an office would be) is even less optimal. I'm not sure I think it's just pushing the problem forward
Then there will also be a push for cheaper, freer energy as well.
3 replies →