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.

Juejin

AI overview

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

Headlines · 4

  1. A SiYuan Note Workflow for AI-Assisted Multi-Platform Publishing

    A Juejin author describes a personal publishing workflow built around SiYuan Note, the AI Creation Workshop plugin and the Metrix plugin. The system reads a local knowledge base, uses models including DeepSeek V4, Claude Sonnet 4.5 and GPT-6 to revise drafts, then creates covers and synchronizes drafts across seven platforms. The author says the workflow takes about 10 minutes, but provides no independent benchmark or verification.

    掘金 · 人工智能 · 🔥 0
  2. Juejin Usage launches desktop local AI gateway

    Juejin Usage announced a desktop local AI gateway that brings provider authorization, model routing, usage history, and local runtime-tool configuration into one interface. According to the vendor announcement, it supports custom API providers, LAN sharing, configurable ports, connectivity testing, and the Messages, Responses, Chat, and Gemini protocols. The update also adds usage collection for CodeArts Agent and PI-Desktop, and allows Trae international accounts to read quota and usage through an existing IDE login.

    掘金 · 人工智能 · 🔥 0
  3. Juejin Announces Winners of 1024 New Rice Bowl AI Campaign

    Juejin announced that its “1024 New Rice Bowl Plan” campaign ended on November 1 and published the winners for discussions about career alternatives and submissions of AI works. The campaign covered AI side projects, work monetization, career Plan Bs, and Vibe Coding projects. Juejin said winners were selected using its rules along with content quality, engagement, completion, and market potential.

    掘金 · 人工智能 · 🔥 0
  4. Juejin test: browser agents read the web better than they write to it

    In a first-person account of running a browser agent through Juejin's daily routine tasks, the author finds that reading pages works well while write actions such as liking and commenting leak: the tool layer can return success while no backend request was sent, so the agent records a like that never happened. The author recommends giving every write action a postcondition (checking for the network request or the UI text changing from “like” to “liked”), stopping on the first miss instead of re-clicking, cooling down and lowering frequency when the platform's risk control intercepts the action, and ending the run and handing back to a human when a CAPTCHA appears. Because a session was auto-compressed mid-run, the author also prescribes a four-part handover summary (completed items with evidence, unfinished items, explicit prohibitions, next-step order) so constraints are not lost. The article groups browser-agent approaches into vision-based control, model-native action spaces, multi-tab operation with human-in-the-loop, and structured DOM or accessibility-tree interaction, and suggests caching-friendly snapshots. The specific agent and model used are not identified.

    掘金 · 人工智能 · 🔥 0

Experience and discussion from the community

Share my Juejin experienceAsk about Juejin

Nobody has shared their experience with Juejin yet.