Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on GPT-3.5 Turbo fine-tuning and API updates. Parent comment
Early testers have reduced prompt size by up to 90% by fine-tuning instructions into the model itself, speeding up each API call and cutting costs.
I wonder if that 90% is precisely due to the calculation you made.
There are no comments on this comment yet.
Early testers have reduced prompt size by up to 90% by fine-tuning instructions into the model itself, speeding up each API call and cutting costs.
I wonder if that 90% is precisely due to the calculation you made.