Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Claude Haiku

AI overview

Sign in and the AI will write an overview from our coverage.

Headlines · 3

  1. Superlite: a Claude Code plugin that parallelizes agent builds

    A developer released Superlite, a Claude Code plugin that plans a build, splits it into tasks that can run side by side, assigns each task to the cheapest Claude model that can do it well (Opus, Sonnet or Haiku), checks the interfaces between tasks and reviews the result. In the author's self-run benchmarks, a smaller sitegen task took 8.8 minutes versus 34.4 minutes for the superpowers workflow, with both passing 89/89 hidden tests; on a 177-test project, three Superlite runs averaged 25.1 minutes versus 33.6 minutes, again passing all tests. The author says hooks enforce rules such as blocking the coordinating agent from editing code and moving test runs to the background, but all performance figures come from the author's own testing and are not independently verified.

    Hacker News 首页（100+ 分） · 🔥 4
  2. Claude Code internals explained: CLAUDE.md, Hooks, Skills and Subagents

    A Juejin author writing as "Silent Wang Er" walks through Claude Code's internals based on its official documentation, starting with the seven kinds of content in the context window and the two-step overflow strategy: clearing older tool outputs first, then summarizing the conversation history, which the author notes can lose earlier instructions. The piece details how four CLAUDE.md layers (managed policy, user, project, local) are concatenated rather than overridden, with an official recommendation to keep each file under 200 lines, and how Hooks enforce rules via exit codes and PreToolUse permission decisions such as allow, deny and ask. It also covers Skills' on-demand loading, a 1536-character cap on each Skill description, a 1% context budget for the skill index list, and the context isolation of the built-in Explore, Plan and General-purpose Subagents, where Explore and Plan skip loading CLAUDE.md and Git status at startup.

    掘金 · 人工智能 · 🔥 3
  3. Engineer's AI pipeline over 400 years of archives finds forgotten meteorite, lost rhinos

    A software engineer, inspired by historian Benjamin Breen's use of Claude Opus 5.5 to find a new dodo eyewitness account, built an AI research pipeline with Claude Code: a cheap "System One" decision model, Jev, first filters huge volumes of passages (reading 59,000 elephant mentions cost about $3), Claude Haiku then reads, translates and extracts dates and places, and a Claude Code agent checks transcriptions against scans of the original manuscripts. The run processed GLOBALISE's 4.35 million transcribed pages of Dutch East India Company records in a single 12-hour overnight pass. The author reports finding an 1812 reprint in the Java Government Gazette of a Bombay letter describing a meteorite fall near Pandharpur, which if confirmed would be the earliest recorded fall in Maharashtra by 26 years, plus archival details of Javan rhinoceroses sent as gifts to the King of Kandy dying en route in 1738–1740.

    Hacker News · AI（100+ 分） · 🔥 0

Experience and discussion from the community

Share my Claude Haiku experienceAsk about Claude Haiku

Nobody has shared their experience with Claude Haiku yet.