Eleven responsible AI objectives supporting AI Governance, with a practical framework, coding companion and downloadable Python exercises.
Stop treating neural networks and loss.backward() as a black box. Build a complete automatic differentiation engine and deep learning library from an empty folder in 100% pure Python—from ScalarNode computation graphs and reverse-mode backpropagation to Multi-Layer Perceptrons, AdamW, BatchNorm1D, and a Character-Level Language Model—explained with visual split-box diagrams, plain-English intuition, and verifiable terminal outputs.
Stop treating Stable Diffusion as a black box. Build a complete, verifiable Text-to-Image Latent Diffusion engine from an empty folder in pure PyTorch—from the Variational Autoencoder (VAE) and CLIP Text Encoder to the Time-Conditioned U-Net, DDPM Noise Scheduler, and Classifier-Free Guidance—explained with crystal-clear visual diagrams, plain-English intuition, and zero hidden magic.
RAG answers you can trace to a source: ingestion, permissions, hybrid search, reranking, evals and regression gates, drawn and built in Python.
Take a character from approved concept to a consistent, usable 3D game asset.
Organize AI generators, jobs, and settings for a repeatable game asset workflow.
Choose AI models for game assets by comparing real jobs, results, and costs.
Write clearer image-generation briefs for consistent game assets.
Give AI agents durable rules, skills, and workflows for solo game development.
Direct AI-assisted game art from visual briefs to final polish. A practical workflow for solo indie developers.
Large language models can write code, solve problems and reason about the world, but how do they actually work? The Ghost in the Weights takes you inside the black box, exploring the tools and techniques researchers use to uncover the algorithms hidden in neural networks. Learn to trace circuits, decode features and turn opaque computations into something you can understand, test and investigate yourself.
Discover how artificial intelligence is transforming scientific research, from hypothesis generation to autonomous experimentation. This book explores the models, algorithms and computational tools driving a new era of discovery, offering researchers and engineers the knowledge to understand, build and apply AI-powered scientific systems.
As AI models become increasingly accessible, the real challenge lies in making them work reliably in production. Advanced Harness Design explores the engineering behind robust AI systems, from architecture and orchestration to security and operations. Discover the patterns, tools and practical techniques needed to build dependable AI systems that perform in the real world.
Go beyond a plausible patch: trace its impact, choose meaningful tests, and make the merge decision reviewable.