News for hackers. Stuff that matters.
Re:Language Model UXes in 2027 by liampulles on Wednesday September 20, 2023 @05:04AM (#37582039)
I'm actively trying to scaffold an LLM for business usecases and my experience totally echoes this. I can tweak the prompt for a very representative set of training data, and then it vomits at a seemingly normal new case.
Re:Language Model UXes in 2027 by arthurcolle on Wednesday September 20, 2023 @05:12AM (#37582100)
have you tried to train a model based on your expectation context data and the outputs you want?