Skip to content
mlmentorship

Book IV

LLMs, agents, and post-training

Transformer internals, inference, retrieval, evaluation, agents, alignment, and post-training.

7 chapters · 42 entries

Chapters

7
IV.1

Transformer architecture and attention

Build from the transformer block to efficient and sparse attention variants.

Scope
Core
Difficulty
Intermediate
Useful for
RS, RE, MLE, AS
IV.2

Tokens, position, and long context

Understand input representation, positional information, and context extension.

Scope
Core
Difficulty
Intermediate
Useful for
RS, RE, MLE, AS
IV.3

Inference and decoding

Move from decoding policy to cache layout, batching, speculation, and test-time compute.

Scope
Role-specific
Difficulty
Advanced
Useful for
RE, MLE, LLM engineer
IV.4

Post-training, alignment, and safety

Preference learning, verifiable rewards, oversight, threats, and red-team design.

Scope
Role-specific
Difficulty
Advanced
Useful for
RS, RE, Safety/evals, Post-training
IV.5

Interpretability and monitoring

Inspect internal mechanisms and reason about monitored chain-of-thought signals.

Scope
Specialist
Difficulty
Advanced
Useful for
RS, Safety/evals
IV.6

Fine-tuning and retrieval-augmented generation

Choose adaptation or retrieval, then design and evaluate the resulting system.

Scope
Role-specific
Difficulty
Intermediate
Useful for
AS, MLE, LLM engineer
IV.7

LLM application and agent design

Handle failure, safety, tools, authority, and product integration in real applications.

Scope
Role-specific
Difficulty
Advanced
Useful for
AS, MLE, RE, LLM engineer