1267 related articles
Deep DivesSimon Willison releases LLM 0.32a0 alpha with message sequences and typed streaming chunks, redefining how Python developers interact with LLMs while maintaining full backward compatibility.
Tech FrontiersSimon Willison releases LLM library 0.32 alpha with message sequences and typed streaming chunks, replacing the old text-in-text-out model to fully support multi-turn dialogue, multimodal output, and tool calling.

Technical analysis of how DeepSeek AI assists in game cheat development, from memory scanning to code generation, exploring AI's role in lowering coding barriers and its implications for game security.

GitHub Trending Aug 15: cordis meta-framework surges 616 stars, Soup enables 8B model fine-tuning on 4GB VRAM, CLI-Anything drives Agent-Native software.

Deep dive into how Prompt Caching works—caching inputs, not outputs. Practical tips to maximize cache hit rates in AI coding agents and cut token costs by up to 90%.

Explore LangChain's technical positioning and learning value for GenAI development, covering core components, course evaluation criteria, and a practical beginner's learning path.

A deep dive into AI Agent development covering LangChain, LangGraph, and CrewAI frameworks, from single-agent to multi-agent collaboration systems.

Agent-Devtools is a 100% local AI Agent debugging tool supporting causal debugging, behavior diff, deterministic replay, and context provenance. No API Key needed, with native LangChain integration.

Deep dive into LangChain 1.3's core value, covering framework learning approaches, AI programming misconceptions, LangGraph and Deep Agent relationships, and building medical multi-agent projects.

PPT Master is an open-source project with over 45K GitHub Stars that generates native editable .pptx files via AI, featuring data charts, animations, voice narration, and custom templates.

Alibaba's Qwen 3.8 model weights are now open-source. This article analyzes Qwen's open-source strategy, the value of weight release for private deployment and fine-tuning, and its competitive position in the global open-source LLM landscape.

Attackers impersonate ClaudeBot and other AI crawlers for mass vulnerability scanning using User-Agent spoofing. Learn attack methods, identification techniques, and defenses including IP verification and WAF configuration.

How can linguistics, localization, and NLU professionals transition in the LLM era? Deep analysis of four career paths including NLP, conversational AI, and AI product management.

Deep dive into DLLM, a minimalist coding agent built directly on llama.cpp. Explore its zero-overhead architecture, local privacy advantages, use cases, and trade-offs vs. cloud AI coding tools.

Hax is a minimalist AI coding assistant written in C that runs natively in the terminal. Zero dependencies, ultra-lightweight, and instant startup — built for terminal workflows.

After completing MNIST implementation and paper reproduction, how should self-taught ML learners advance? This article outlines three paths: computer vision, NLP, and math foundations.

Complete guide to LangChain AI Agent tool calling: from defining tools with @tool decorator to automatic Agent invocation, with calculator examples, security tips, and naming conventions.

A systematic LLM learning roadmap: from Python basics to LangChain & LlamaIndex frameworks, RAG, Agent, and fine-tuning core skills, plus hands-on projects to master LLM app development in 3 months.

Learn how Java engineers can enter AI application development using Spring AI to build an enterprise-grade airline intelligent customer service system with RAG, Function Calling, and more.

Needle is a 14MB open-source foundation model from cactus-compute, designed for phones, wearables, smart home devices, and robots. Explore its edge AI potential.