5 learnings from classifying 500k customer messages with LLMs vs traditional ML

July 13, 2023

#classification   #actual work   #shortcomings and inflated expectations   #link  

I love how absolutely bland the results are:

LLMs aren't perfect, but they're pretty good. Fine-tuned traditional models are also pretty good. Be careful when you're putting your data and prompts together. b Life is like that sometimes.

Source: https://www.trygloo.com/blog/classify-text-llms-learnings

Permalink