Skip to content
TopicTracker
From HackerNewsView original
TranslationTranslation

HT-ML.app – Deploy HTML Artifacts from Claude Code and Codex

HT-ML.app is a tool that allows users to deploy HTML artifacts directly from Claude Code and Codex, streamlining the process of sharing and hosting web-based outputs.

Background

- **HT-ML.app** is a lightweight web service that lets developers take HTML artifacts (self-contained web pages, dashboards, prototypes) generated by AI coding assistants and instantly deploy them to a live URL. - **Claude Code** and **Codex** are AI-powered coding tools (from Anthropic and Cursor, respectively) that can generate HTML/CSS/JS output. Until now, sharing that output meant copy-pasting or using separate hosting services. - The service solves a practical friction: AI-generated front-end code is often thrown away because there's no quick way to show it to others. HT-ML makes that one-click, with a public link. - It matters because it lowers the barrier between "AI made this" and "here, look at this working page" — useful for designers, educators, and anyone iterating on UI ideas with an LLM.

Related stories

  • Newer Claude models sometimes invent extra keys in tool call arguments, breaking validation in Pi's edit tool. The author suspects post-training for Claude Code's forgiving harness makes alternative schemas fail. This suggests closed RL training can degrade general tool-use reliability.

  • Simon Willison released llm-coding-agent 0.1a0, an experimental coding agent built on his LLM library. The agent provides tools for reading, editing, searching files and executing commands, and ships with a Python API and CLI. It was developed using Claude Code (Fable 5) via TDD with a spec-first approach, and is available as a slop-alpha on PyPI.

  • Truth Social remains an outlet primarily for Trump's own posts, while other administration officials continue using X. The platform functions as a blog-like channel for Trump's messages rather than a genuine social network competitor.