In Context Learning

Flashcard: how does Reflexion let an agent learn from failed runs?

Flashcard: what is few shot prompting and what does the 'few' actually refer to?

Three concrete situations where fine-tuning is the wrong tool

Explain why in-context learning in a RAG pipeline is functionally equivalent to approximate Bayesian inference even though no parameters are updated, citing the relevant theoretical results.

When an LLM in a RAG pipeline behaves differently because of the retrieved context, what is actually changing about the model?

You're prompting GPT-5.5 for English-to-Spanish translation. The zero-shot version works fine. When would adding few-shot examples reliably outperform the zero-shot prompt?

How does DSPy reframe prompt engineering and what does it gain over hand-written prompts?

Why does the ORDER of few-shot examples in a prompt measurably affect output quality and where should the most-representative example go?

How does Reflexion enable an agent to learn from failed attempts without fine-tuning the model?