Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on The Inference Cost of Search Disruption – Large Language Model Cost Analysis. Parent comment
Huh it literally uses real throughput figures
> doesn’t account for ways to make things cheaper over time
It does in the subscriber section and it says it does say that in the free section.
> We already have papers that suggest most big models are undertrained and smaller models can get the same accuracy.
Why assume 2023 model is the same as 2020 GPT-3 175B parameter
There are no comments on this comment yet.
Huh it literally uses real throughput figures
> doesn’t account for ways to make things cheaper over time
It does in the subscriber section and it says it does say that in the free section.
> We already have papers that suggest most big models are undertrained and smaller models can get the same accuracy.
Why assume 2023 model is the same as 2020 GPT-3 175B parameter