Volume 3 of 3 · PDF edition

Volume 3: Scaling, Alignment, and Agentic AI

Scaling laws, retrieval, multimodal models, instruction tuning, open models, alignment, long context, reasoning, and the rise of agents.

The complete book remains free to read online. This paid edition is the carefully typeset PDF you keep, with every future update included.

Pages
338 pages
Chapters
45 chapters
Price
$14 one-time
Buy nowLearn more
History of Language AI, Volume Three: Scaling, Alignment, and Agentic AI cover

Author and edition details

About the author and Volume 3 PDF edition

Michael Brenndoerfer, author of History of Language AI

Michael Brenndoerfer

Michael has spent more than a decade working across software engineering, data, AI, and business. He writes to understand difficult ideas more deeply and to share what he learns in a clear, practical way.

Report an error or suggest a correction
Edition
Volume 3 PDF 2026.08.2
Published
Last reviewed

Historical through-line

What this volume explains

  • Connect scaling, retrieval, and data choices to the capabilities of foundation models.
  • Trace instruction tuning, alignment, open-model development, multimodality, and modern evaluation.
  • Place long-context reasoning and agentic systems inside the broader historical arc of language AI.

Audience and prerequisites

Who this volume is for

Readers who want a technically grounded history of foundation models, alignment, and agentic AI.

Prerequisites: Readable on its own; familiarity with transformers is helpful and is developed historically in Volume 2.

Free online preview

Start with “Scaling Laws (2020)”

Kaplan et al. discovered power-law scaling relationships between model size, data, compute, and performance, enabling prediction of model capabilities and optimal resource allocation

Read the chapter

Exact contents

45 chapters across 4 parts

Scaling & Retrieval

  1. 01Scaling Laws (2020)
  2. 02GPT-3 & In-Context Learning (2020)
  3. 03Dense Passage Retrieval & RAG (2020)

Multimodal & Instruction Era

  1. 01Mixture-of-Experts at Scale (2021)
  2. 02CLIP (2021)
  3. 03Codex (2021)
  4. 04Instruction Tuning (2021)
  5. 05Multi-Vector Retrievers (2021)
  6. 06The Pile (2021)
  7. 07DALL·E (2021)
  8. 08Foundation Models Report (2021)
  9. 09InstructGPT & RLHF (2022)
  10. 10Chinchilla Scaling Laws (2022)
  11. 11HELM (2022)
  12. 12Chain-of-Thought Prompting (2022)
  13. 13ChatGPT (2022)
  14. 14BLOOM (2022)
  15. 15PaLM (2022)
  16. 16Flamingo (2022)
  17. 17DALL·E 2 (2022)
  18. 18Stable Diffusion (2022)
  19. 19Whisper (2022)
  20. 20FlashAttention (2022)

Open Models & Alignment

  1. 01LLaMA (2023)
  2. 02Open LLM Wave (2023)
  3. 03QLoRA (2023)
  4. 04Function Calling & Tool Use (2023)
  5. 05Multimodal LLMs (2023)
  6. 06Constitutional AI (2023)
  7. 07BIG-bench & MMLU (2023)
  8. 08GPT-4 (2023)

Agents, Long Context & Real-Time AI

  1. 01Mixtral & Sparse MoE (2024)
  2. 02Long Context at Scale (2024)
  3. 03Structured Outputs (2024)
  4. 04Hybrid Retrieval (2024)
  5. 05PEFT Beyond LoRA (2024)
  6. 06Continuous Post-Training (2025)
  7. 07Mixture of Experts at Scale (2024)
  8. 08Agentic AI Systems (2024)
  9. 09Multimodal Integration (2024)
  10. 10DeepSeek R1 (2025)
  11. 11GPT-4o (2025)
  12. 12V-JEPA 2 (2025)
  13. 13AI Co-Scientist Systems (2025)
  14. 14Specialized LLMs for Low-Resource Languages (2025)

Volume 3 PDF

Own this 338-page edition

Get the PDF and every future update and erratum for this volume. Your purchase is fully credited toward the complete edition.

  • Carefully typeset PDF
  • Future updates and errata included
  • Portable offline reading
  • Delivered by email and added to My books

Volume 3 of 3

$14

one-time

Version 2026.08.2 · 338 pages · secure checkout via Stripe

Delivered by email · Free updates included

Compare editions

This volume or the complete book?

Volume 3: Scaling, Alignment, and Agentic AI

338 pages focused on Scaling & Retrieval and Multimodal & Instruction Era and Open Models & Alignment and Agents, Long Context & Real-Time AI.

$14

The complete History of Language AI

All three volumes in one 968-page PDF. Three distinct volume purchases unlock it automatically; two volumes leave a $6 complete-edition upgrade.

$34

Compare all PDF editions

Also in the series

Explore the other volumes

Volume 1 · 324 pages

Signals, Symbols, and Statistical Methods

Signals & Symbols · The Statistical Turn

Explore Volume 1

Volume 2 · 319 pages

Neural Networks, Attention, and Transformers

Structured Learning & Benchmarks · Deep Learning Arrives · Transformers & Pretraining

Explore Volume 2

Version history

Kept current, not frozen in time

Each PDF purchase includes future editions. When the book changes, the updated copy appears in My books at no extra cost.

Current release

Edition 2026.08.2

Editorial improvements.

Earlier releases2

  1. 2026.08.1

    Editorial improvements throughout the book, with clearer explanations, refined presentation, and improved plots and visualizations.

  2. 2026.08.0

    Initial complete-book and three-volume PDF release with perpetual updates.