The Complete Obsolete Guide to Generative AI

brief contents
contents
foreword
preface
acknowledgments
about this book
	About the code
	liveBook discussion forum
about the author
about the cover illustration
1 Understanding generative AI basics
	Stepping into the generative AI world
	Categorizing AI models by function and objective
		Understanding usage tokens
		GPT-4 models
		GPT-3.5 models
		GPT-3 models
	Model fine-tuning
	The technologies that make generative AI work
	AI and data privacy and ownership
	AI and reliability
	What’s still ahead?
2 Managing generative AI
	Accessing GPT models
	Learning by playing
	Accessing Python code samples
	Accessing curl code samples
	Completion configurations
		Setting the mode
		Setting the temperature
		Setting the Top P value
		Working with stop sequences
		Setting the frequency penalty
		Setting the presence penalty
		Working with Best Of
		Working with the Inject Start Text setting
3 Creating text and code
	Automating accuracy checking
	Creating new contextually aware content
		Setting up your environment for Python
		Creating your prompt (using Python)
	Generating specialized documents
	Generating programming code
	Interactive coding with Copilot
	Try this for yourself
4 Creating with media resources
	Generating images
		Providing detailed prompts
		Prompting for images
	Generating video
		AI-assisted video editing
		Text-to-video slide shows
	Generating presentation resources
	Generating voice
	Audio transcriptions
	Generating music
	Try this for yourself
5 Feeding data to your generative AI models
	Indexing local data archives
	Seeding a chat session with private data (ChatPDF)
	Connecting your AI to the internet (Auto-GPT)
	Try this for yourself
6 Prompt engineering: Optimizing your experience
	What is prompt engineering?
	Prompt engineering best practices
		Be specific
		Be clear
		Avoid unnecessary words
		Separate reference text from your instructions
		Be positive, not negative
		Control for temperature (randomness)
	Zero-shot and few-shot prompting
	Prompt for time-series data: A practical example
		Visualizing the data
		Graphing the time-series data without normalization
		Graphing the time-series data with normalization
	Try this for yourself
7 Outperforming legacy research and learning tools
	Asking for investment guidance
	Connecting search engines to AI using LangChain
	Using LangChain to analyze multiple documents
	Teaching yourself to program, to speak a new language,or anything else
	Integrating LLMs into your daily work
		Spreadsheet integration
		Kanban integration
		Slack integration
		Salesforce integration
		Code version control
		Photoshop integration
	Try this for yourself
8 Understanding stuff better
	Using GPT to replace analytics
	Using GPT to replace sentiment analysis
		Some background to sentiment analysis
		Testing sentiment analysis through GPT
	Try this for yourself
9 Building and running your own largel anguage model
	Some background to building your own model
	Selecting a base LLM model for configuration
	Configuring and building your model
	Fine-tuning your model
		Creating a dataset
		Training your model
	Creating your own GPT
10 How I learned to stop worrying and love the chaos
	What the workers of the world can reasonably expect
	What your next business startup will look like
	Artificial general intelligence: Where it’s all going
	Should AI be regulated?
	The road ahead
		Quantum computing
		Neuromorphic computing
		Advanced hardware acceleration
		Reinforcement learning and meta-learning
		Multimodal learning
		Explainability and interpretability
		Data efficiency and few-shot learning
		Domain-specific knowledge integration
	Second-order effects
		Investment markets
		Human innovation
		Employment markets
		On-demand media
		On-demand journalism
11 Experts weigh in on putting AI to work
	Including projects discussed in your book, where have you had the greatest success applying AI to solving practical problems?
		Daniel Sanz Becerril
		Leo Porter and Daniel Zingaro
		Chrissy LeMaire
		Paul McFedries
	What would you say is the most transformational generative AI use case right now in your corner of the IT world?
		Chrissy LeMaire
		Daniel Sanz Becerril
		Leo Porter and Daniel Zingaro
		Paul McFedries
	What’s the next big thing you see AI bringing to the world that very few people yet anticipate?
		Leo Porter and Daniel Zingaro
		Daniel Sanz Becerril
		Paul McFedries
		Chrissy LeMaire
	What’s the most fun you’ve ever had interacting with generative AI?
		Chrissy LeMaire
		Paul McFedries
		Daniel Sanz Becerril
		Leo Porter and Daniel Zingaro
	What was your most spectacular generative AI-fueleddisaster and/or disappointment?
		Chrissy LeMaire
		Leo Porter and Daniel Zingaro
		Nathan Crocker
		Daniel Sanz Becerril
		Paul McFedries
	Do you see recent reports about GitHub Copilot losing significant money on each monthly account as indications that we haven’t yet figured out a sustainable gen AI model, or is it just a temporary blip?
		Daniel Sanz Becerril
		Chrissy LeMaire
		Paul McFedries
		Leo Porter and Daniel Zingaro
	Could you share some of the AI tools you’re using. Do you have any tips or warnings for readers experimenting with generative AI?
		Paul McFedries
		Chrissy LeMaire
		Leo Porter and Daniel Zingaro
		Nathan Crocker
A Important definitionsand a brief history
	Some critical AI definitions
	A very (very) brief history of AI
B Generative AI resources
	General LLM interaction tools
	AI application development platforms
	Third-party tools
	Writing tools
	Image generation
	Data analytics
	Investment and financial
	Speech-to-text
	Text-to-speech
	Text-to-music
	Text-to-video
	Text-to-video presentations (including animated and lifelike avatars)
	Slide deck generation
	Text, audio, and video language translation
	Domain specific
C Installing Python
	Installing Python on Windows
	Installing Python on macOS
	Installing the pip Python package manager on Linux
index