News for hackers. Stuff that matters.
Re:GPT-3.5 Turbo fine-tuning and API updates by Xenoamorphous on Tuesday August 22, 2023 @03:54PM (#37227740)
From https://twitter.com/OfficialLoganK/status/169406294917713961...

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.