chinese

Tag

Cards List
#chinese

@komereji12: The Chinese edition of Stanford’s Agent tutorial is here! 19 lessons + 4 hands-on projects covering LLMs, RAG, tool calling, memory, multi-agent systems, and evaluation, with offline HTML reading support. Want to know how to actually build an AI agent? Start with this tutorial series.

X AI KOLs Timeline ↗ · 2026-10-31 Cached

A Chinese-language self-study tutorial for Stanford’s CS329Z “Engineering AI Agents” course has been released, featuring 19 lectures and 4 hands-on exercises covering LLMs, RAG, tool calling, memory, multi-agent systems, and evaluation, with support for offline HTML reading.

0 favorites 0 likes
#chinese

@hassanyehiaa: I've received a lot of direct messages these past two days, and many tutors and teachers have offered suggestions — I'm truly grateful. I've been continuously improving the knowledge graph content, and based on everyone's feedback, I've increased the difficulty levels of the question banks as well as expanded the number of questions. Details are as follows: Difficulty tiers: Questions for each knowledge point are divided into three tiers — Basic, Advanced, and Extension. Diagnostic order: Present the Advanced question first; if answered correctly, use an Extension question to confirm mastery. If answered incorrectly, follow up with a Basic question; if still incorrect, trace back to related knowledge points from earlier grades, with the prerequisite knowledge highlighted on the interface.

X AI KOLs Timeline ↗ · 2026-10-28 Cached

The author updated the open-source K-12 knowledge graph project cn-math-taxonomy, adding three difficulty tiers (Basic/Advanced/Extension) of questions for each knowledge point, and improving the adaptive diagnostic order and prerequisite backtracking logic. The project covers math, Chinese, science, English, and physics, and provides an online diagnostic tool, though the author notes it is an AI-generated draft that still awaits teacher review.

0 favorites 0 likes
#chinese

Patronizing and Condescending Language Detection in English and Mandarin

arXiv cs.AI ↗ · 2026-10-26

This paper proposes an automated system for detecting patronizing and condescending language (PCL) in English and Mandarin, comparing a static word embedding + CNN approach with fine-tuned BERT embeddings, which achieved an F1 score of 0.528 on the development set.

0 favorites 0 likes
#chinese

@Michaelzsguo: If you said today was the worst day in the history of internet security, I doubt you could find a second day to challenge it for that title. This post sums it up perfectly. I translated it paragraph by paragraph without breaking the original style.

X AI KOLs Timeline ↗ · 2026-10-22 Cached

A tweet lamenting that today was the worst day in the history of internet security: PHP dropped two critical vulnerabilities on the same day, allowing attackers to execute code remotely without logging in, and details leaked before patches were even released, affecting major systems such as WordPress, MediaWiki, Magento, Joomla, and Laravel. The author faithfully translated the original post into Chinese, preserving its style.

0 favorites 0 likes
#chinese

@FinanceYF5: 2/ Over the past decade, the compute used to train AI models has grown by 10 million times. Meanwhile, the duration of tasks AI can complete autonomously doubles every few months. Models are shifting from answering questions to independently carrying out increasingly long tasks.

X AI KOLs Timeline ↗ · 2026-10-19 Cached

Over the past decade, the compute used to train AI models has grown by 10 million times, the duration of tasks AI can complete autonomously doubles every few months, and models are shifting from answering questions to independently carrying out longer work.

0 favorites 0 likes
#chinese

@FinanceYF5: 1/ An Anthropic researcher told a room full of PhD students: "The career paths you originally planned no longer exist." The talk was titled "The End of the Humanocene," and the data in it was brutal.

X AI KOLs Timeline ↗ · 2026-10-19 Cached

An Anthropic researcher told a room full of PhD students in a talk titled "The End of the Humanocene" that the career paths they had originally planned no longer exist, and the data presented was quite brutal.

0 favorites 0 likes
#chinese

@YxzRainy: Fun fact: Although DeepSeek V4.1 Flash 1017 has "Flash" in its name, its parameter count is a whopping 763B — larger than quite a few flagship models

X AI KOLs Timeline ↗ · 2026-10-18 Cached

A fun fact post points out that despite having "Flash" in its name, DeepSeek V4.1 Flash 1017 has a whopping 763B parameters, making it larger than quite a few flagship models.

0 favorites 0 likes
#chinese

@antiAIvo: Essential MoE Reading: "Switch Transformer" — The Core Ideas of Sparse Large Models Explained Clearly I've been studying this paper recently and broke it down into three parts, each with runnable test code to help you understand: https://nano-ai.tech/papers/?share=2…

X AI KOLs Timeline ↗ · 2026-10-16 Cached

A Chinese tutorial that breaks down Google's 2021 Switch Transformer paper into a three-part series, covering MoE with Top-1 routing, expert capacity and load balancing, training stability and experimental findings — with runnable test code included.

0 favorites 0 likes
#chinese

@Jaden_riku: Lately, besides creating my own original content, I've also been browsing a ton of information online every day. Among …

X AI KOLs Timeline ↗ · 2026-10-10 Cached

A translated and compiled article outlining ten principles of good design from Paul Graham's 'Taste for Makers,' including simplicity, standing the test of time, solving the right problem, leaving room, humor, hard work, seeming effortless, symmetry, learning from nature, and constant revision.

0 favorites 0 likes
#chinese

@jinchenma_ai: AI Noun Crash Course, Second Edition is Here! When using AI daily, what exactly are these functions—deep thinking, reasoning intensity, planning mode, goal mode—meant for? This article breaks down the common terms in everyday tools with specific scenarios.

X AI KOLs Timeline ↗ · 2026-10-04 Cached

This is an introductory article on AI terminology (Part 2), systematically explaining common functional concepts in everyday AI tools—such as prompt engineering, system prompts, custom instructions, reasoning and chain-of-thought, deep thinking and reasoning effort, question-answering/execution mode, plan mode, and goal mode—and their use cases.

0 favorites 0 likes
#chinese

@HytidelLegend: Learn Any Knowledge 10x Faster with AI Open Source Repository: https://github.com/HytidelLegend/htd-ai-augmented-educat…

X AI KOLs Timeline ↗ · 2026-10-04 Cached

开源项目 htd-ai-augmented-education 发布 v0.1.11,包含 18 个面向学生、教师和科研工作者的 AI Agent Skills 与学习应用,可集成到豆包、Claude Code、Codex、Cursor 等支持 Skills 的 Agent 中,用于 AI 辅助学习、背诵记忆、英语写作和播客生成等场景。

0 favorites 0 likes
#chinese

Beyond Atomic Tokens: Factorizing Syllables for Language Model Pretraining

arXiv cs.CL ↗ · 2026-09-21 Cached

This paper introduces a linguistically motivated phonemic tokenizer for Vietnamese and Chinese that factorizes syllables into onset, rime, and tone components, reducing vocabulary size and improving efficiency. The proposed PhonemicBERT models demonstrate competitive or superior performance in language understanding tasks compared to existing tokenizers and pretrained models.

0 favorites 0 likes
#chinese

HSK Manga: Turning Manga into Beginner-Level Chinese

Lobsters Hottest ↗ · 2026-08-30 Cached

HSK Manga is a free tool that simplifies manga dialogue to HSK levels for Chinese learners, using AI and OCR to make reading more accessible for beginners.

0 favorites 0 likes
#chinese

@crblandet: Speaking of the ICT trading model, a while ago I compiled a Chinese tutorial using Fable 5 (burned through most of my weekly quota) and put it on my website. First author is Fable 5, corresponding author is me. Welcome to human or AI distillation https://chanlunpp.org/basics-ict

X AI KOLs Timeline ↗ · 2026-08-14 Cached

The Chinese tutorial on the ICT trading model, created using Fable 5, is now online, systematically explaining the core concepts and trading system.

0 favorites 0 likes
#chinese

@XAMTO_AI: Want to write a coding agent yourself? You've read plenty of articles about the principles, but you get stuck at the first line when you actually start. Recently I found the Chinese tutorial *Hands-On Pi*, which starts with a real offline agent log and takes you through all 15 levels from the beginning. Truly build a complete coding agent from scratch—every step has runnable code...

X AI KOLs Timeline ↗ · 2026-08-13 Cached

Introduces the Chinese tutorial *Hands-On Pi*, covering the step-by-step implementation of a Pi-style coding agent from scratch through 15 runnable checkpoints, including protocols, tool loops, conversation tree storage, context compression, and evaluation. Each chapter comes with the main text, a corresponding commit, tests, and failure experiments.

0 favorites 0 likes
#chinese

@Suu766: You've already used a VPN to get on Telegram, but still can't search for resources — it's really a waste!!! Many people are looking for groups, channels, and bots, and still begging in the comments for someone to send links. Actually, someone has already organized Chinese TG resources for you. Channels, groups, bots, tool resources — you can find them directly by searching keywords, saving you from searching high and low in Telegram…

X AI KOLs Timeline ↗ · 2026-08-09 Cached

Recommend using tgzhidao.com, a Chinese Telegram navigation site. Users can search channels, groups, bots, and tool resources by keywords, avoiding the need to search for a needle in a haystack in Telegram.

0 favorites 0 likes
#chinese

@grgerwcwetwet: Played Telegram for a long time, still don't know where to find quality channels? Recommend a practical website TG知道, which specifically collects Chinese Telegram channels, groups, and bots. It covers tech & digital, learning & tech, news, communities, practical bots, etc. Direct category search, much more convenient than randomly searching around in Telegram yourself…

X AI KOLs Timeline ↗ · 2026-08-08 Cached

Recommend a website called TG知道, which specifically collects Chinese Telegram channels, groups, and bots, supports categorized search, making it convenient for users to discover quality resources.

0 favorites 0 likes
#chinese

Hy-MultiTurn: A Six-Dimensional Benchmark for Deep Multi-Turn Dialogue Understanding

arXiv cs.CL ↗ · 2026-08-03 Cached

Introduces Hy-MultiTurn, a Chinese benchmark for deep multi-turn dialogue understanding, evaluating 22 frontier models across six controlled modes (constraint memory, precise execution, constraint synthesis, object localization, action suppression, reference resolution) with 209 tasks spanning 12-76 turns. Even the strongest model, GPT-5.5, satisfies only 41.1% of responses.

0 favorites 0 likes
#chinese

@jinchenma_ai: Removing AI flavor is not something that can be solved with a set of prompts or an open-source skill. If you want to remove AI flavor as cleanly as possible and make your writing more like yourself, you need to build an iterative, compounding writing system for yourself.

X AI KOLs Timeline ↗ · 2026-08-02 Cached

Jinchenma shares how to remove AI flavor through an iterative personal writing system, including clarifying author identity, article types, taboo rules, and methods for multiple independent reviews and rule iteration.

0 favorites 0 likes
#chinese

@seclink: mimofan has built-in the following 29 features: 1. Tool call loop breaker (DEFAULT_MAX_CONTINUATIONS = 50) 2. Auto-compaction mechanism (http://compaction.rs) 3. Token usage tracking (T…

X AI KOLs Timeline ↗ · 2026-07-29 Cached

The mimofan tool has built-in 29 features, including tool call loop breaker, auto-compaction mechanism, token usage tracking, system prompt optimization, etc. It is a feature-rich AI agent tool.

0 favorites 0 likes
Next →
← Back to home

Submit Feedback