Model Selection & Provider Landscape

37 lessons in AI Engineering / Working with LLMs

• Starting Simple and Upgrading When NeededSlides / Video
• Avoiding Provider Lock-InSlides / Video
• Latency and Speed Across ModelsSlides / Video
• Model Versions, Snapshots, and DeprecationSlides / Video
• Matching Model Choice to Task TypeSlides / Video
• Evaluating Models on Your Own Use CaseSlides / Video
• Why Benchmarks Can Be MisleadingSlides / Video
• Model Benchmarks and LeaderboardsSlides / Video
• Balancing Cost, Quality, Speed, CapabilitySlides / Video
• Comparing Pricing Across ModelsSlides / Video
• Comparing Context Window SizesSlides / Video
• Flagship vs Small Model TiersSlides / Video
• Why Model Selection MattersSlides / Video
• What Model Selection MeansQuiz
• Flagship vs Small ModelsQuiz
• Model Naming ConventionsQuiz
• Where to Access ModelsQuiz
• Leaderboards and BenchmarksQuiz
• Quality vs Cost TradeoffsQuiz
• Latency as a Selection FactorQuiz
• Start with a Default and IterateQuiz
• Model Families and VersionsQuiz
• Context Window as Selection FactorQuiz
• Matching Model to TaskQuiz
• Reasoning vs Standard ModelsQuiz
• Cost as a Selection FactorQuiz
• Quality as a Selection FactorFlashcard
• Benchmarks and LeaderboardsFlashcard
• Major LLM ProvidersFlashcard
• What Model Selection MeansFlashcard
• Matching Model to Task ComplexityFlashcard
• Model Naming and VersioningFlashcard
• Model Families and TiersFlashcard
• Prototype Strong, Then OptimizeFlashcard
• Model Deprecation and LifecycleFlashcard
• Avoiding Vendor Lock-InFlashcard
• Specialized ModelsFlashcard