Web Developer
New web development articles are posted weekly, mainly focused on frontend topics.
Reparsing the whole LLM response on every chunk recreates elements and loses state such as text selection. streamAppendHTML() returns a WritableStream that parses HTML onto the end of an element. This article covers its usage and sanitization.
Claude now supports MCP Tasks and Elicitation. Tasks turn slow tool calls into a task ID plus polling, and Elicitation asks the user for input mid-operation. This article builds an MCP server with the TypeScript SDK and calls it from Claude Code.
Safari 27.1 ships the Device Posture API and Viewport Segments API behind feature flags for foldables like iPhone Duo. This article explains how both APIs work, how they evolved, and how to build layouts that avoid the fold.
Reparsing the whole LLM response on every chunk recreates elements and loses state such as text selection. streamAppendHTML() returns a WritableStream that parses HTML onto the end of an element. This article covers its usage and sanitization.
Claude now supports MCP Tasks and Elicitation. Tasks turn slow tool calls into a task ID plus polling, and Elicitation asks the user for input mid-operation. This article builds an MCP server with the TypeScript SDK and calls it from Claude Code.
Safari 27.1 ships the Device Posture API and Viewport Segments API behind feature flags for foldables like iPhone Duo. This article explains how both APIs work, how they evolved, and how to build layouts that avoid the fold.
azukiazusa
azukiazusa
azukiazusa
azukiazusa
Improve memory and skills with the Boy Scout Rule
A talk about gradually improving an agent's memory and skills through everyday tasks, so it can accomplish work more efficiently.
The frontend's audience has changed: designing new web interfaces in the age of AI
Frontend engineers have always built for humans — but AI is changing that assumption. This talk examines two shifts: AI as a producer of web output (streaming UI, MCP Apps) and AI as a consumer of the web (Markdown delivery, WebMCP), exploring what these changes mean for how we design web interfaces in the AI era.
How should we give feedback when coding agents write frontend code?
LLM-based coding agents (such as Claude Code and Codex) are spreading rapidly, and feedback from code execution results is essential in iterative improvement loops. Backend development can get immediate feedback through execution and tests, while frontend development has unique challenges. This talk focuses on the feedback-loop problem in frontend code generation and discusses practical solutions and trade-offs.
