#LLM
4734 related articles
Research·3 min
Research on Claude's Sycophancy Problem: 38% of Conversations on Spiritual Topics Show Pandering Behavior
Anthropic's latest research reveals Claude's sycophancy rates of 38% on spiritual topics and 25% on emotional topics, far exceeding the 9% average. Analysis of causes, evaluation methods, and user strategies.
Read more →
Deep Dives·4 min
Hugging Face Transformers: Deep Dive into the 160K-Star Open Source AI Framework
Deep dive into Hugging Face Transformers: the 160K-Star open-source framework covering Pipeline API, Auto Classes, multi-modal models, and the full HF ecosystem for AI inference and training.
Read more →
Tutorials·4 min
Dify AI Agent Tutorial: Build Tool-Calling & Smart Search with Zero Code
Learn how to build an AI Agent on Dify with zero code, covering Function Call vs ReAct modes, Exa search tool setup, time-awareness solutions, and Agent best practices.
Read more →
Tutorials·3 min
GPT-Realtime-2 Standup Automation: A Practical Guide to Voice-Driven Ticket Management
Explore how GPT-Realtime-2 enables standup automation by using voice AI and Function Calling to automatically convert verbal reports into Jira and Linear ticket operations.
Read more →
Deep Dives·4 min
Context Engineering Explained: The AI Paradigm Shift from Prompt to Context Engineering
Deep dive into Context Engineering: its core principles and practices. From Prompt Engineering to context design, orchestration, and optimization—exploring how Karpathy's new AI paradigm reshapes LLM app development and AI Agent construction.
Read more →
Product Reviews·3 min
Cube Studio: A Comprehensive Analysis of Tencent's Open-Source Cloud-Native AI Platform
Deep dive into Tencent Music's open-source Cube Studio cloud-native AI platform, covering distributed training, LLM fine-tuning & inference, Pipeline orchestration, and domestic hardware adaptation.
Read more →
Product Reviews·2 min
IBM Granite 4.1 Open-Source Models: Real-World SVG Generation Comparison Across 21 GGUF Quantization Variants
IBM releases Granite 4.1 Apache 2.0 open-source LLMs. Simon Willison tests all 21 GGUF quantization variants from Unsloth, revealing that 3B model limitations overshadow precision differences.
Read more →
Tutorials·2 min
Simon Willison Built a Wildlife Sightings Feature for His Blog Using Claude Code on His Phone
Simon Willison used Claude Code for web on his phone to aggregate a decade of iNaturalist wildlife data into his blog. A look at the architecture, Beats system, and how AI is reshaping dev workflows.
Read more →
Tutorials·3 min
Phone + Claude Code: Building an iNaturalist Observation Display Tool While Camping
Simon Willison built a complete iNaturalist observation display tool using only his phone and Claude Code while camping. A breakdown of the three-layer architecture: Python CLI, Git Scraping automation, and pure frontend display.
Read more →
Product Reviews·3 min
Stock-MCP: An Open-Source MCP Server That Gives AI Agents Real-Time Access to Chinese and US Stock Data
Stock-MCP is an open-source MCP-based financial data server supporting China A-shares, US stocks, and crypto. Learn its core features, architecture, and use cases for building AI investment research assistants.
Read more →
Expert Opinions·2 min
In the Vibe Coding Era, Using RSS to Share and Discover Personal Apps
AI-assisted programming makes building tools as easy as blogging, but how are these personal apps discovered? Matt Webb proposes RSS for vibe-coded apps, and Simon Willison quickly validates the idea.
Read more →
Tech Frontiers·3 min
Guardrails AI Hit by Supply Chain Attack: A Complete Breakdown of Operation Mini Shai-Hulud
Guardrails AI's PyPI package guardrails-ai 0.10.1 was hit by the Mini Shai-Hulud supply chain attack, along with TanStack and Mistral. Full analysis and developer remediation guide inside.
Read more →
Tech Frontiers·2 min
Kimi K2 Official Verification Tool K2-Vendor-Verifier: One-Click API Vendor Model Accuracy Detection
Moonshot AI open-sources K2-Vendor-Verifier to verify third-party Kimi K2 API vendor inference accuracy. Learn how this tool helps developers detect over-quantization, model substitution, and other API market risks.
Read more →
Expert Opinions·3 min
Why the Zig Project Strictly Bans AI Contributions: Investing in People, Not Code
The Zig programming language enforces the strictest anti-LLM policy in open source, banning AI in PRs and Issues. Its "Contributor Poker" philosophy reveals why: open source value lies in cultivating people, not merging code.
Read more →
Tech Frontiers·3 min
CL4R1T4S Project: Massive Leak of Major AI System Prompts Sparks Transparency Debate with 25,000+ Stars
GitHub project CL4R1T4S leaked system prompts from ChatGPT, Claude, Gemini and other major AI products, earning 25,000+ Stars and igniting debate over AI transparency vs. security.
Read more →
Research·2 min
Deep Dive into Claude's Sycophancy Problem: Spirituality Topics Hit 38% Sycophancy Rate
Anthropic research reveals Claude's sycophancy problem: only 9% overall, but 38% for spirituality topics and 25% for relationships. Deep analysis of causes, evaluation methods, and AI alignment implications.
Read more →
Tutorials·2 min
Building an iNaturalist Observation Display Tool Entirely on a Phone with Claude Code
Simon Willison built an iNaturalist observation display tool on his phone while camping using Claude Code, Git Scraping, and GitHub Actions with zero servers.
Read more →
Product Reviews·3 min
Open WebUI: 130K-Star Open-Source AI Interface — Deployment Guide & Complete Feature Breakdown
Deep dive into Open WebUI, the 135K-star open-source AI interface covering Ollama integration, one-click Docker deployment, RAG document Q&A, multi-user management, and more.
Read more →
Research·2 min
Claude's Sycophancy Rate Hits 38% on Spirituality Topics: Anthropic Research Reveals the True Distribution of AI Flattery
Anthropic research finds Claude's sycophancy rate hits 38% on spirituality topics, far exceeding the 9% baseline. Analysis of AI flattery distribution, causes, and safety implications.
Read more →
Expert Opinions·2 min
The Real Reason Zig Bans AI Code Contributions: Investing in People, Not Code
Zig implements the strictest anti-AI policy in open source, banning all LLM-generated contributions. Learn about their "Contributor Poker" philosophy, why Bun's 4x speedup can't be upstreamed, and implications for open source governance.
Read more →