News for hackers. Stuff that matters.
Re:GPT-3.5 Turbo fine-tuning and API updates by hnuser123456 on Wednesday August 23, 2023 @07:43AM (#37234388)
It seems like LLMs can easily start to "forget" requests to modify their style or tone if it's a small part of the overall context, and they drift back towards the style or tone they naturally have (or were encouraged to have by their original trainers.)

There are no comments on this comment yet.