AI/LLM Books 2 hours ago
#1
AI / LLM Recommended Reading List
Here's my collection of essential AI and Large Language Model books organized by tier.
Must Read
1. AI Engineering: Building Applications with Foundation Models
Author: Chip Huyen
Synopsis: A practical guide focusing on the architectural principles, patterns, and best practices required to design, build, and deploy production-ready applications powered by foundation models and LLMs.
2. Build a Large Language Model (From Scratch)
Author: Sebastian Raschka
Synopsis: Step-by-step instructions on creating a fully functioning LLM from the ground up using PyTorch, covering tokenization, self-attention mechanisms, pre-training, and fine-tuning.
3. Hands-On Large Language Models
Author: Jay Alammar & Maarten Grootendorst
Synopsis: An accessible, visually rich introduction to understanding, implementing, fine-tuning, and using LLMs for real-world Natural Language Processing tasks.
4. Designing Machine Learning Systems
Author: Chip Huyen
Synopsis: A comprehensive, end-to-end framework for designing machine learning systems that are reliable, scalable, maintainable, and adaptable to real-world production environments.
5. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
Author: Aurélien Géron
Synopsis: A concrete, hands-on guide using practical Python tools to understand machine learning concepts and build deep neural networks.
Solid Book
6. LLM Engineer’s Handbook
Author: Paul Iusztin & Maxime Labonne
Synopsis: An end-to-end practical manual for building, fine-tuning, evaluating, and serving large language models at scale in production systems.
7. Designing Multi-Agent Systems
Author: Victor Dibia
Synopsis: Explores principles, patterns, and practical code implementations for building collaborative, autonomous AI agent teams to solve complex tasks.
8. Building Applications with AI Agents
Author: Michael Alcorn
Synopsis: Focuses on designing, building, and deploying autonomous and multi-agent systems using modern frameworks and tools.
9. Natural Language Processing with Transformers
Author: Lewis Tunstall, Leandro von Werra, & Thomas Wolf
Synopsis: A hands-on walkthrough on using Hugging Face Transformers to build, fine-tune, and deploy state-of-the-art NLP models.
10. Designing Data-Intensive Applications
Author: Martin Kleppmann
Synopsis: A definitive technical deep-dive into the core principles, trade-offs, and architectures behind reliable, scalable, and maintainable data storage and processing systems.
Good Read
11. Prompt Engineering for LLMs
Author: John Berryman & Albert Ziegler
Synopsis: Details the techniques, art, and science behind effective prompt formulation to build resilient language model applications.
12. Building LLMs for Production
Author: Towards AI (Louie Peters et al.)
Synopsis: A practical guide covering prompt engineering, RAG, fine-tuning, and model evaluation to scale modern AI solutions into robust production environments.
13. AI Agents in Action
Author: Lanham
Synopsis: Focuses on building, configuring, and deploying practical AI agents capable of autonomous decision-making and workflow execution.
14. Prompt Engineering for Generative AI
Author: James Phoenix & Mike Taylor
Synopsis: Teaches practical prompt design strategies, structured inputs, and optimization techniques for repeatable, reliable generative AI outputs.
15. The Hundred-Page Language Models Book
Author: Andriy Burkov
Synopsis: A concise, highly accessible introduction explaining how language models work, complete with code snippets using PyTorch.
Read Later
16. Deep Learning
Author: Ian Goodfellow, Yoshua Bengio, & Aaron Courville
Synopsis: The foundational theoretical textbook covering broad concepts in deep learning, linear algebra, probability, neural network architecture, and deep generative models.
17. The Hundred-Page Machine Learning Book
Author: Andriy Burkov
Synopsis: A compact overview covering core classical and modern machine learning algorithms, math foundations, and practical guidance in a brief format.
18. Co-Intelligence: Living and Working with AI
Author: Ethan Mollick
Synopsis: Examines how generative AI impacts work, education, and human collaboration, offering practical strategies for effectively partnering with AI.
19. Why Machines Learn: The Elegant Math Behind Modern AI
Author: Anil Ananthaswamy
Synopsis: Explores the mathematical concepts, historical milestones, and foundational ideas that power modern artificial intelligence and machine learning algorithms.
20. The Alignment Problem: Machine Learning and Human Values
Author: Brian Christian
Synopsis: An investigation into how machine learning models learn human biases, default choices, and implicit assumptions, and how researchers are working to keep AI safe and aligned with human values.
Here's my collection of essential AI and Large Language Model books organized by tier.
Must Read
1. AI Engineering: Building Applications with Foundation Models
Author: Chip Huyen
Synopsis: A practical guide focusing on the architectural principles, patterns, and best practices required to design, build, and deploy production-ready applications powered by foundation models and LLMs.
Spoiler:
2. Build a Large Language Model (From Scratch)
Author: Sebastian Raschka
Synopsis: Step-by-step instructions on creating a fully functioning LLM from the ground up using PyTorch, covering tokenization, self-attention mechanisms, pre-training, and fine-tuning.
Spoiler:
3. Hands-On Large Language Models
Author: Jay Alammar & Maarten Grootendorst
Synopsis: An accessible, visually rich introduction to understanding, implementing, fine-tuning, and using LLMs for real-world Natural Language Processing tasks.
Spoiler:
4. Designing Machine Learning Systems
Author: Chip Huyen
Synopsis: A comprehensive, end-to-end framework for designing machine learning systems that are reliable, scalable, maintainable, and adaptable to real-world production environments.
Spoiler:
5. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
Author: Aurélien Géron
Synopsis: A concrete, hands-on guide using practical Python tools to understand machine learning concepts and build deep neural networks.
Spoiler:
Solid Book
6. LLM Engineer’s Handbook
Author: Paul Iusztin & Maxime Labonne
Synopsis: An end-to-end practical manual for building, fine-tuning, evaluating, and serving large language models at scale in production systems.
Spoiler:
7. Designing Multi-Agent Systems
Author: Victor Dibia
Synopsis: Explores principles, patterns, and practical code implementations for building collaborative, autonomous AI agent teams to solve complex tasks.
Spoiler:
8. Building Applications with AI Agents
Author: Michael Alcorn
Synopsis: Focuses on designing, building, and deploying autonomous and multi-agent systems using modern frameworks and tools.
Spoiler:
9. Natural Language Processing with Transformers
Author: Lewis Tunstall, Leandro von Werra, & Thomas Wolf
Synopsis: A hands-on walkthrough on using Hugging Face Transformers to build, fine-tune, and deploy state-of-the-art NLP models.
Spoiler:
10. Designing Data-Intensive Applications
Author: Martin Kleppmann
Synopsis: A definitive technical deep-dive into the core principles, trade-offs, and architectures behind reliable, scalable, and maintainable data storage and processing systems.
Spoiler:
Good Read
11. Prompt Engineering for LLMs
Author: John Berryman & Albert Ziegler
Synopsis: Details the techniques, art, and science behind effective prompt formulation to build resilient language model applications.
Spoiler:
12. Building LLMs for Production
Author: Towards AI (Louie Peters et al.)
Synopsis: A practical guide covering prompt engineering, RAG, fine-tuning, and model evaluation to scale modern AI solutions into robust production environments.
Spoiler:
13. AI Agents in Action
Author: Lanham
Synopsis: Focuses on building, configuring, and deploying practical AI agents capable of autonomous decision-making and workflow execution.
Spoiler:
14. Prompt Engineering for Generative AI
Author: James Phoenix & Mike Taylor
Synopsis: Teaches practical prompt design strategies, structured inputs, and optimization techniques for repeatable, reliable generative AI outputs.
Spoiler:
15. The Hundred-Page Language Models Book
Author: Andriy Burkov
Synopsis: A concise, highly accessible introduction explaining how language models work, complete with code snippets using PyTorch.
Spoiler:
Read Later
16. Deep Learning
Author: Ian Goodfellow, Yoshua Bengio, & Aaron Courville
Synopsis: The foundational theoretical textbook covering broad concepts in deep learning, linear algebra, probability, neural network architecture, and deep generative models.
Spoiler:
17. The Hundred-Page Machine Learning Book
Author: Andriy Burkov
Synopsis: A compact overview covering core classical and modern machine learning algorithms, math foundations, and practical guidance in a brief format.
Spoiler:
18. Co-Intelligence: Living and Working with AI
Author: Ethan Mollick
Synopsis: Examines how generative AI impacts work, education, and human collaboration, offering practical strategies for effectively partnering with AI.
Spoiler:
19. Why Machines Learn: The Elegant Math Behind Modern AI
Author: Anil Ananthaswamy
Synopsis: Explores the mathematical concepts, historical milestones, and foundational ideas that power modern artificial intelligence and machine learning algorithms.
Spoiler:
20. The Alignment Problem: Machine Learning and Human Values
Author: Brian Christian
Synopsis: An investigation into how machine learning models learn human biases, default choices, and implicit assumptions, and how researchers are working to keep AI safe and aligned with human values.
Spoiler:
If you need help accessing these, please let me know. I can try to fish them out again and update this thread.
![[Image: mivrgxw.gif]](https://i.imgur.com/mivrgxw.gif)
![[+]](https://sinister.ly/images/modern/collapse_collapsed.png)
