Why aren't we fine-tuning more? (1 minute read)

TLDR AI
Machine Learning AI Research

A good prompt can do a lot of the work that fine-tuning does without the cost. Models are getting so good that fine-tuning isn't really required to get good results. The extra work and resources required for fine-tuning aren't worth it anymore for most use cases. It is still worth knowing how to fine-tune, as there are other situations where the skill is useful.