Introduction & Core Concepts

51 lessons in AI Engineering / Working with LLMs

• Next-Token Prediction: The Core MechanismSlides / Video
• LLMs vs Traditional SoftwareSlides / Video
• Popular LLM Models and ProvidersSlides / Video
• What a Large Language Model IsSlides / Video
• Temperature and RandomnessQuiz
• Non-Deterministic OutputsQuiz
• System Prompt vs User PromptQuiz
• Next-Token PredictionQuiz
• Knowledge CutoffQuiz
• The Context WindowQuiz
• Popular LLM ProvidersQuiz
• What Is a Large Language ModelQuiz
• Parameters and Model SizeQuiz
• LLMs vs Rule-Based ProgramsQuiz
• Hallucinations ExplainedQuiz
• Common LLM Use CasesQuiz
• Tokens and TokenizationQuiz
• The Transformer ArchitectureQuiz
• Pretraining BasicsQuiz
• API vs Chat InterfaceQuiz
• Open-Source vs Proprietary ModelsQuiz
• Prompts and CompletionsQuiz
• Non-determinism in LLM OutputsSlides / Video
• Limitations of LLMsSlides / Video
• Model Parameters and Model SizeSlides / Video
• Common LLM Use Cases and ApplicationsSlides / Video
• Context Window and Its LimitsSlides / Video
• Prompts and CompletionsSlides / Video
• How LLMs Learn Language PatternsSlides / Video
• Tokens and Tokenization BasicsSlides / Video
• Key LLM TerminologySlides / Video
• Common Examples of LLMsFlashcard
• HallucinationsFlashcard
• Common LLM Use CasesFlashcard
• The Transformer ArchitectureFlashcard
• Temperature and Output ControlsFlashcard
• LLMs vs Rule-Based SoftwareFlashcard
• What is AI EngineeringFlashcard
• What is a PromptFlashcard
• What is a CompletionFlashcard
• Tokens and TokenizationFlashcard
• Parameters and Model SizeFlashcard
• Base vs Instruction-Tuned ModelsFlashcard
• Next-Token PredictionFlashcard
• Context WindowFlashcard
• What is a Large Language ModelFlashcard
• Non-Determinism of OutputsFlashcard
• System, User, Assistant RolesFlashcard
• Knowledge CutoffFlashcard
• Training Data and PretrainingFlashcard
• APIs vs Chat InterfacesFlashcard