Lessons
Explore all newline lessons
lesson
Tokens and EmbeddingsPower AI course- Tokenization as dictionary for model input - Tokens → IDs → contextual embeddings - Semantic meaning emerges only in embeddings - Transformer layers reshape embeddings by context - Pretrained embeddings accelerate domain understanding - Good tokenization reduces loss, improves learning - Tokenizer choice impacts RAG chunking - Compression tradeoffs differ by domain needs - Tokenization affects inference cost and speed - Compare BPE, SentencePiece, custom tokenizers - Emerging trend: byte-level latent transformers - Generations of embeddings add deeper semantics - Similarity measured via dot products, distance - Embeddings enable search, clustering, retrieval systems
lesson
Securing a Svelte Application with JSON Web TokensFullstack SvelteSecuring the application with JSON Web Tokens
lesson
How to Create Design Tokens and Styles in FigmaThe newline Guide to React Component Design Systems with FigmagicLet's move on from basics to the intermediate level and actually make some designs.
lesson
An Intro to Figmagic, the Figma CLI For Token DesignThe newline Guide to React Component Design Systems with FigmagicFigmagic is the last piece in our toolchain that acts as the glue needed to super-charge your productivity.
lesson
Intro to Design Tokens: How to Communicate in Design WorkThe newline Guide to React Component Design Systems with FigmagicOne magic, simple concept (design token) and a one-stop shop to contain our design equal one hell of a powerhouse.
lesson
How to Build a Token Authentication Server With DenoBuild and deploy a REST API with DenoYou will learn how to make a simple token authentication in Deno
lesson
How to Use Tailwind CSS With JavaScript Design TokensBuild a Complete Company Design SystemStyling React components with Tailwind CSS preset