alt Hacker News> Can't wait for the unlimited plans we will have in due time.
I don't see how this can happen. The cost of serving a model grows linearly with use (energy). The cost of serving a mobile data plan is approximately zero.
> Can't wait for the unlimited plans we will have in due time.
I don't see how this can happen. The cost of serving a model grows linearly with use (energy). The cost of serving a mobile data plan is approximately zero.
> The cost of serving a model grows linearly with use (energy)
The cost of processing tokens however does not. Throughput and efficiency are improving around 10x per year. Hardware is not the only factor.