Sat 20 May 2023

Against LLM maximalism

A lot of people are building truly new things with Large Language Models (LLMs), like wild interactive fiction experiences that weren’t possible before. But if you’re working on the same sort of Natural Language Processing (NLP) problems that businesses have been trying to solve for a long time, what’s the best way to use them?

Source: Against LLM maximalism, an article by Matthew Honnibal.