Context & In-Context Learning
Autoregressive generation, the prompt stack, context engineering, and long-context degradation.
10concepts
88flashcards
74minutes of reading
- 01 Context Compaction and Handoff When an agent's conversation approaches the window limit, compaction summarises the history and reinitialises a fresh window from the summary; what survives the compression determines whether the agent continues or silently restarts.
- 02 Context Engineering The discipline of curating exactly which tokens occupy the model's window during inference, and why it became the core skill for building agents that run longer than a single turn.
- 03 In-Context Learning How large models learn a task from examples in the prompt alone, with no weight updates, and why this emergent ability reframed how we use LLMs.
- 04 Many-Shot In-Context Learning What changes when you put hundreds or thousands of examples in the prompt instead of five, why the gains keep coming after few-shot plateaus, and how model-generated rationales substitute for scarce human data.
- 05 RAG vs Long Context The engineering decision the million-token window forced, what controlled comparisons actually found about quality and cost, and why routing between retrieval and full-context beats picking a side.
- 06 The Prompt Stack and Chat Roles What a chat prompt actually is under the hood: a single token sequence built from system, user, and assistant turns wrapped in special tokens, and why that structure is load-bearing.