Flashcard

Flashcard: what is chain-of-thought (CoT) prompting, in one sentence?

Flashcard: what is a token in LLM prompting and why does it matter for cost and context?

Flashcard: what is a vector database, and why does RAG need one?

Flashcard: what is similarity search in RAG, and how does it differ from keyword search?

Flashcard: what does 'grounding' mean in the context of RAG, and why is it the whole point?

Flashcard: what is an embedding in a RAG pipeline, and what role does it play?

Flashcard: what does chunking mean in RAG, and why do we chunk at all?

Flashcard: what role does the LLM's context window play in a RAG pipeline?

What is STRR and how does it complement fertility as a tokenizer fairness metric?

What are BOS, EOS, PAD, and role marker special tokens, and what happens when each is missing or duplicated?

What are BPE merge residues (LiteToken) and what do they imply for vocabulary efficiency?

How does byte-level BPE guarantee no unknown tokens, and what is the cost of that guarantee?

What constraint does BoundlessBPE relax, and what improvement does it yield?

Flashcard: is a 0.85 cosine similarity score from your retriever 'high confidence'?

Flashcard: name the three augmentation sub-decisions in a production RAG pipeline.

What are the three message roles in a chat-style LLM prompt and what does each represent?

Define prompt engineering and identify what it actually touches.

At which architectural layer does MCP sit versus vendor function calling?

What problem does A2A solve that MCP does not?

What is tool poisoning in MCP?

Does MCP sandbox its servers at the protocol level?

Is MCP an Anthropic-only technology?

What integration problem does MCP solve?

Why string-match accuracy fails as an LLM evaluation metric

What is shadow deployment for LLMs and how does it enable safe evaluation?