Books

"The model is safe." "The filter is effective." "We red-teamed it and found nothing." "Wereviewed a sample and it looked fine." Each of those is a claim about evidence, and each is unfalsifiable as stated. Reviewing thirtyoutputs and finding no problems is consistent with a failure rate of one in eleven. Threehundred tests against a thousand possible failure modes leave seven hundred nobody looked at. This book supplies the missing arithmetic — and it was written without generating a singleharmful output to study.

Quantise the weights. Batch the requests. Add a draft model. Prune what you can. Shorten thecache. A long list of techniques and a short list of reasons. This book measures the reason first: the machine streams memory at 22.54 GB/s and computes at116.58 GFLOP/s, so anything performing fewer than 5.17 operations per byte is waiting. Decodingperforms 0.22. Every technique in the book is then measured against that one number — andseveral turn out to be addressing the wrong side of it.

Понятный иллюстрированный путеводитель по ключевым концепциям и практическим применениям больших языковых моделей. Идеально подходит для работы над проектами, подготовки к собеседованиям и самостоятельного обучения.

هذا الكتاب هو دليل مختصر وموضّح بالرسوم لأي شخص يرغب في فهم الآلية الداخلية للنماذج اللغوية الضخمة، سواء في سياق المقابلات أو المشاريع أو بدافع الفضول الشخصي.

The practitioner's guide to policy-space response oracles: one 84-line loop, one readable repository, and every claim backed by a committed experiment — including the ones that came out wrong.

Use LoRA because it forgets less. Keep the learning rate low. Mix in some general data. Stopearly. Four pieces of advice everyone repeats and almost nobody quantifies. This book measures each one — and two turn out to be doing something other than what they arecredited with. LoRA's retention is governed by a scaling constant, not by its parameterefficiency. Early stopping bounds the damage without separating it from the gain. Everyexperiment reports two numbers: the new task, and the capability you were not trying tochange.

Chunk at 500 with 50 of overlap. Retrieve five. Add a reranker. Use hybrid search.Repeated everywhere, justified almost nowhere. This book measures them instead, on corpora built so that the correct answer follows fromhow they were made. Several results contradicted the advice: the hybrid combination lost inevery condition tested, neither reranker produced an effect above the noise floor, andattribution collapsed to 0.170 while retrieval was still reporting 0.920.

Vector databases give you a similarity metric, an index with four tuning parameters, acompression option and a way to filter — and almost no guidance on what any of it costs. This book builds each one from scratch and measures it. The proximity graph, the invertedfile, the product quantiser: implemented in NumPy, included with the text, and checkedagainst exhaustive search — so every recall figure here is exact rather than estimated.

A machine can hand you a grouping that is confident, stable, internally consistent, and seven times worse than the one it found a moment earlier. Nothing in the output says so.This book works k-means through completely on twelve bakery customers, small enough that every number is printed and checkable. You will build the method from nothing, see exactly where it succeeds, and see exactly where it fails silently.Fifty-eight figures, every one captured from a running implementation.

Prompting has more advice than evidence. This book measures it instead: a model reading apattern it has never seen, the same model failing at a task in one pass and solving itperfectly in four, a decoder that guarantees a format instead of improving the odds, and amodel that is 2.4% accurate while 78.6% confident. Six central claims are built from scratch and measured on a single CPU core. Everythingtaken from published research sits in a grey box marked "Not measured here" — so you neverhave to guess which is which.

From your first JAX script to large-scale AI systems, this book shows how to write faster, cleaner Python for modern computing. Learn the ideas behind JAX through practical examples, real projects and clear explanations that help you build everything from scientific simulations to distributed machine learning.

Learn how to design, build, and deploy reliable, scalable, and maintainable Machine Learning systems in production through an iterative end-to-end process.

Build a world-class technical publishing brand with this complete guide to designing, structuring, and publishing professional Tech Capsules. Learn proven layouts, visual identity, content architecture, publishing workflows, and best practices used to create high-quality technical micro-books that readers lov

Every news feed is full of AI buzzwords: Transformers, tokens, embeddings, context windows, hallucinations, objective functions. Yet most explanations are either dense academic textbooks or empty marketing fluff. ☕ Coffee Break AI is your practical guide to AI. Written in plain English with warm real-world analogies. It breaks down the core mechanisms of AI into 40 bite-sized chapters.

If you want to build real NLP applications instead of just experimenting with notebooks, spaCy is one of the best places to start. This book walks you through the entire journey from the fundamentals to advanced production workflows with practical explanations, real code examples and hands-on projects that show you how to build fast, reliable NLP systems for the real world.