chinese

An open-source hands-on book "Hands-On Large Language Models", with 12 chapters covering language model fundamentals, prompt engineering, semantic search, model fine-tuning, and multimodal applications. It provides runnable code examples, ideal for practical learning.

A Twitter user shared a carefully curated collection of Claude Code learning resources, including Chinese tutorials, command tips, skill libraries, etc., for beginners to get started.

This tutorial introduces the Loop Engineering method, which designs a cycle of automatic execution, checking, and correction, allowing AI to iterate until the result is satisfactory, upgrading a single query into process engineering.

Introduces multiple web scraping tools, including yt-dlp, FxTwitter, get笔记, etc., for scraping content from different platforms.

Toku Reader is a language learning app that lets users read and listen to native Japanese and Chinese content, with tap-to-translate functionality.

The user praised a product launched by Baidu that effectively solves the pain point of dealing with numbers when translating papers, considering it a necessity.

A Chinese quantitative finance tutorial for absolute beginners, using Jupyter Notebook format, containing 4 chapters (quantitative cognition, return analysis, dual moving average strategy, and strategy backtesting). Uses yfinance to fetch real data, each chapter can be run through in about 30 minutes.

Introduces LingxiDiagBench, a large-scale multi-agent benchmark for evaluating LLMs on Chinese psychiatric consultation and diagnosis. Key findings show high accuracy on binary classification but poor performance on multi-way differential diagnosis, highlighting a decoupling between conversational quality and diagnostic accuracy.

A 4-level learning roadmap from beginner to expert in using Claude, packed with practical tutorial links to save users half a year of exploration time.

The AI-generated content from Seedance 2.0 is incredibly realistic, almost absurd, showcasing 10 stunning examples.

An open-source learning roadmap project called Agent-Learning-Hub, which breaks down AI Agent learning into 8 stages from building a minimal Agent loop to production deployment, providing executable todo lists and recommended resources, maintained by members of the Datawhale community.

Anthropic shared best practices for implementing self-service data analysis with Claude, achieving 95% automation of business analysis queries with an overall accuracy of about 95%, and detailed the agent analysis tech stack, three main failure modes, and corresponding countermeasures.

A developer shares various development pitfalls encountered when mixing Chinese and overseas large models for viber coding, including timezone, data types, database design, security vulnerabilities, etc., advising beginners to use it with caution.

An open-source project that enables AI Agents to generate beautifully formatted Chinese PPTs through non-destructive text editing, providing 17 hand-crafted Chinese PPTX templates and a complete toolchain.

This is an open-source project on GitHub that aggregates ebook resources from multiple Chinese reading apps, categorizes them, and supports downloading in multiple formats.

The paper introduces CITA, a framework for generating implicit toxicity attacks in Chinese to evaluate and improve LLM toxicity detectors, finding high attack success rates across tested models.

This paper introduces Psy-Chronicle, a structured framework for synthesizing long-horizon campus psychological counseling dialogues, and releases CPCD, a Chinese dataset of 90,000 dialogues across multiple sessions, along with a benchmark for evaluating models on long-horizon counseling capabilities.

Recommends 8 Chinese tech/AI podcasts covering AI, entrepreneurship, business interviews, etc., including Silicon Valley 101, Zhang Xiaojun's Business Interview Series, Crossing, etc., suitable for listeners interested in AI and tech business.

Teacher Alin demonstrates how to configure an interpreter for the Obsidian clipping plugin using the DeepSeek v4 flash model. The operation is simple and can be completed in one minute.

Recommend a Chinese-subtitled tutorial on building AlphaGo from scratch, suitable for learning AI and reinforcement learning.