#LLM compiler
217 related articles
Tutorials·3 min
Implementing LangGraph in TypeScript: Deconstructing the Core Principles of AI Agent Frameworks from Scratch
Learn how to implement LangGraph's core design from scratch in TypeScript, covering state-graph-driven architecture, node-based orchestration, and the ReAct pattern for AI Agent development.
Read more →
Tutorials·4 min
Claude Code Hands-On Tutorial: Installation, DeepSeek Integration & Programming Tips - Complete Guide
Complete guide to Claude Code installation, DeepSeek V4 Pro integration, IDE setup, with a real full-stack project demo, Skill system, MCP configuration, and 10 AI programming tips.
Read more →
Deep Dives·3 min
D2C Design-to-Code Full Pipeline Explained: The New Design-Development Paradigm That Top Tech Companies Ask About in Interviews
A deep dive into D2C (Design to Code) technology, comparing it with traditional development and Vibe Coding, covering Figma AI implementation, three-level interview questions, and enterprise architecture design.
Read more →
Tech Frontiers·4 min
OpenAI's $3B Windsurf Acquisition: How AI Is Reshaping the Programming Landscape
OpenAI acquires AI coding tool Windsurf for $3B. We break down the three-layer strategic logic, the impact on programmer jobs, and the rise of AI product managers.
Read more →
Tutorials·4 min
Stagehand Tutorial: An AI Browser Automation Framework That Balances Control and Intelligence
Deep dive into Stagehand's four core capabilities: Act, Extract, Observe, and Agent. Learn to build browser automation that balances AI flexibility with code control using DeepSeek as a low-cost alternative to OpenAI.
Read more →
Product Reviews·3 min
AIFlowy: A Java-Based Alternative to Dify for Enterprise AI Application Development
AIFlowy is an open-source AI app development platform built on Java, rivaling Dify and Coze with visual workflow orchestration, multi-model support, and RAG capabilities for enterprise teams.
Read more →
Deep Dives·4 min
Harness Engineering Explained: The Third-Generation Development Paradigm for Taming AI Agents
Deep dive into Harness Engineering: the third-gen AI development paradigm. Learn its three-layer architecture for effectively harnessing AI Agents to complete complex development tasks.
Read more →
Tutorials·3 min
4-bit QLoRA Fine-tuning LLaMA 3 in Practice: A Guide to Training 8 Billion Parameter LLMs on Consumer GPUs
Learn how to fine-tune LLaMA 3 8B on consumer GPUs using QLoRA and Unsloth. Covers 4-bit quantization, LoRA adaptation, Alpaca data format, training pipeline setup, and model deployment—runs on RTX 3090.
Read more →
Tech Frontiers·3 min
Cursor's Parent Company Anysphere Uses Composer to Train Next-Gen AI: How Bootstrapped Iteration Is Changing Code Generation
Anysphere uses previous-gen Composer to build RL training environments for next-gen Cursor AI. Explore how bootstrapped AI training reshapes code generation and the competitive landscape.
Read more →
Expert Opinions·3 min
Zig Language Bans AI Code Contributions: A Deep Debate on Open Source Principles
Zig founder Andrew Kelley rejects LLM-assisted PRs, introducing the concept of AI code's "digital smell." A deep analysis of the open source philosophy, code quality, and trust issues behind Zig's ban on AI contributions.
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 →
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 →
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 →
Tutorials·3 min
Using LLMs as Script Interpreters: Shebang Lines Turn Natural Language into Executable Scripts
Simon Willison shows how putting LLM CLI tools in shebang lines turns plain English text files into executable scripts, from basic usage to tool calls and YAML templates.
Read more →
Product Reviews·4 min
OpenClaw4J: Deep Dive into a Java 21 + Spring AI Agent Framework
Deep dive into OpenClaw4J, an intelligent Agent framework built on Java 21 virtual threads and Spring AI, supporting tool calling, memory management, and multi-Agent collaboration for enterprise Java developers.
Read more →
Product Reviews·4 min
cased/kit: An Open-Source Toolkit for Context Engineering in AI Coding — Code Search and Symbol Extraction
cased/kit is an open-source Python toolkit for context engineering, providing AI coding assistants with codebase mapping, symbol extraction, and multi-mode code search capabilities.
Read more →
Tech Frontiers·3 min
Swarm IDE: Open-Source Multi-Agent Collaborative Development Environment with 1500 Stars for Agent Orchestration
Swarm IDE is an open-source IDE for Agent Swarm multi-agent collaboration, supporting Kimi-2.5, GLM-4.7 and more models with visual orchestration, debugging and management capabilities.
Read more →
Tutorials·3 min
Unsloth Tutorial: Fine-Tune LLMs Locally with Multi-fold Speed Boost and 60% VRAM Savings
Unsloth is an open-source LLM fine-tuning tool with 63K GitHub stars, supporting Gemma 4, Qwen3, and DeepSeek. It achieves multi-fold training speedup and 60% VRAM reduction through kernel optimization, enabling fine-tuning on consumer GPUs.
Read more →
Tutorials·2 min
Unsloth Tutorial: A Guide to Fine-Tuning LLMs Locally with Reduced VRAM and Faster Training
Learn how Unsloth enables efficient local LLM fine-tuning with LoRA optimization, supporting Gemma 4, Qwen3, and DeepSeek while reducing VRAM usage by 50% and boosting training speed 2-5x.
Read more →
Tech Frontiers·2 min
Claude Memory Compiler: An Open-Source Solution for Giving AI Coding Assistants Persistent Memory
Claude Memory Compiler is an open-source project that builds an evolving memory system for Claude Code through a three-layer automated pipeline, solving the persistent amnesia problem of AI coding assistants.
Read more →