Fresher / New Grad

You hear 'fertility is 2.5 for Hindi on cl100k_base'. What does that number mean and is it good?

A tokenizer is 'byte-level'. What does that buy you over a character-level one?

Your teammate mentions BPE at a code review. What are they talking about?

A chat template wraps every turn with BOS and EOS tokens. Why does the model need them?

You need to count tokens locally. When do you reach for tiktoken versus SentencePiece?

Character, word, and subword tokenization each have a dominant failure mode. Match them.

BPE and WordPiece both merge subwords. What is the one thing they disagree on?

BPE grows the vocabulary by adding merges. Unigram does the opposite. Explain the difference.

Flashcard: what is an agent 'trajectory' and why does it matter for evaluation?

What does one agent trace capture step by step?

Flashcard: why use Tree of Thoughts search on hard agent planning problems?

Flashcard: why break a complex goal into subtasks before acting?

Flashcard: why must every agent loop declare when to stop?

Where does an agent keep short-term state during a single task?

Flashcard: how is self-correction different from self-refine in agents?

Why run agent-generated code inside an isolated sandbox?

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

Flashcard: what is the ReAct pattern for agents, in one sentence?

Flashcard: when would you pick Plan-and-Execute over ReAct?

What does observability mean for production LLM agents, and how is it different from app monitoring?

How is a team of agents different from one agent with a large tool belt?

Flashcard: why connect agents through MCP?

How is long-term memory typically implemented in an agent?

When should a production agent pause for human approval?

How does function calling enable the observe-plan-act agent loop?