Language Models are Few-Shot Learners

The 2020 paper that made prompting the new programming.

In 2020, OpenAI scaled a language model to 175 billion parameters and discovered something unexpected: at that size, the model no longer needed retraining to learn new tasks. You could just show it a few examples in the prompt — and it figured the rest out on its own. This bundle unpacks how GPT-3 shattered the fine-tuning paradigm and turned "prompt engineering" into a discipline.