Volume 3: The Modern Frontier: Scale, Intelligence, and What Comes Next4/10
  1. 01Systems at Scale 201-210
  2. 02Modern Data Systems 211-220
  3. 03Machine Learning 221-230
  4. 04Generative AI Systems 231-240
  5. 05Security and Privacy 241-250
  6. 06Emerging Computing 251-260
  7. 07Technology and Society 261-270
  8. 08Digital Economics 271-280
  9. 09Responsible Futures 281-290
  10. 10Synthesis 291-300

Chapter 04 of 10

Generative AI Systems 231-240

10 lessons57 min readingParts 231-240
  1. 01Tokens and Context WindowsHow does a language model break down and remember a conversation?6 min read
  2. 02EmbeddingsHow can text, images, or products become searchable by meaning?6 min read
  3. 03Vector DatabasesWhat kind of database supports similarity search over embeddings?6 min read
  4. 04Retrieval-Augmented GenerationHow can an AI answer using current or private documents?6 min read
  5. 05Prompt DesignWhat makes an instruction easier for a generative model to follow?6 min read
  6. 06Tool-Using AI AgentsHow can a model do more than produce text?5 min read
  7. 07AI EvaluationHow can a team measure whether an AI feature is actually good enough?6 min read
  8. 08Guardrails and Content SafetyHow can an AI application reduce harmful or disallowed behavior?5 min read
  9. 09Fine-TuningWhen should a model's behavior be adjusted through additional training?5 min read
  10. 10AI Cost, Latency, and QualityWhy is the most capable model not always the best product choice?6 min read