BestHub
Sign in
Cambridge Mofang Notes
Author

Cambridge Mofang Notes

Upholding classic programming, focusing on AI human‑machine collaboration, technology implementation and practice sharing.

13
Articles
0
Likes
8
Views
0
Comments
Recent Articles

Latest from Cambridge Mofang Notes

13 recent articles
Cambridge Mofang Notes
Cambridge Mofang Notes
Sep 9, 2026 · Artificial Intelligence

Clearing AI Confusion: Function Calling, MCP, Tools, Skills, Vectors, Tensors, Tokens, Embeddings

This article clarifies commonly confused AI concepts by grouping them into four categories: model-tool interaction (Function Calling vs MCP), task execution (Tools vs Skills), internal data representation (vectors vs tensors), and text processing (Tokens vs Embeddings), explaining their distinct roles and relationships.

EmbeddingFunction CallingMCP
0 likes · 27 min read
Clearing AI Confusion: Function Calling, MCP, Tools, Skills, Vectors, Tensors, Tokens, Embeddings
Cambridge Mofang Notes
Cambridge Mofang Notes
Sep 7, 2026 · Backend Development

Points System Architecture: Concurrency, Batch Expiration & Idempotent Reconciliation

This article walks through designing a points system architecture, starting from a concrete scenario of consuming 80 points across two batches with retries and refunds, covering data models, idempotency keys, local transactions, cache-aside, event-driven reconciliation, scaling strategies, and evolutionary deployment phases.

batch expirationcache-asideevent-driven
0 likes · 27 min read
Points System Architecture: Concurrency, Batch Expiration & Idempotent Reconciliation
Cambridge Mofang Notes
Cambridge Mofang Notes
Sep 4, 2026 · Artificial Intelligence

Model Distillation: Teaching Small Models to Learn from Large Ones

This article explains model distillation through a question rewriting example, detailing how teacher models provide demonstrations to train smaller student models, the differences between distillation, fine-tuning, and quantization, and practical pitfalls like data quality and student capacity limits.

Data QualityKnowledge Distillationfine-tuning
0 likes · 19 min read
Model Distillation: Teaching Small Models to Learn from Large Ones
Cambridge Mofang Notes
Cambridge Mofang Notes
Sep 3, 2026 · Artificial Intelligence

AI Model Types, Quantization & File Formats: A Complete Guide

This article explains the four key dimensions of AI models—purpose, modality, quantization, and file format—covering model categories like LLMs, vision, audio, embedding, and reranker models, multimodal concepts, quantization trade-offs (FP16, Q4, Q8), and formats such as Safetensors, GGUF, and ONNX, with a practical checklist for model selection.

GGUFSafetensorsaudio models
0 likes · 27 min read
AI Model Types, Quantization & File Formats: A Complete Guide
Cambridge Mofang Notes
Cambridge Mofang Notes
Sep 2, 2026 · Artificial Intelligence

How LLM Applications Are Built: Workflows, Agents, MCP & Skills

This article explains the architecture of large language model applications, distinguishing between simple chat, fixed workflows, autonomous agents, the Model Context Protocol (MCP) for tool integration, and reusable skills, providing a decision framework for choosing the right approach based on task complexity and stability requirements.

AI architectureAgentLLM applications
0 likes · 18 min read
How LLM Applications Are Built: Workflows, Agents, MCP & Skills
Cambridge Mofang Notes
Cambridge Mofang Notes
Sep 2, 2026 · Artificial Intelligence

Inference Frameworks vs Platforms: How LLMs Actually Run on Your Hardware

This article distinguishes between inference frameworks (llama.cpp, vLLM, SGLang) that execute model computations and inference platforms (Ollama, LM Studio, Xinference) that manage deployment, explaining their roles, interactions, and how to choose tools for local or server-side LLM inference.

AI inferenceLLM servingLM Studio
0 likes · 16 min read
Inference Frameworks vs Platforms: How LLMs Actually Run on Your Hardware
Cambridge Mofang Notes
Cambridge Mofang Notes
Sep 1, 2026 · Artificial Intelligence

From Dense to MoE: Decoding Total vs. Activated Parameters

This article explains the distinction between total and activated parameters in Mixture-of-Experts (MoE) models, contrasting dense and sparse architectures, detailing expert routing mechanisms, and analyzing memory and compute implications across model loading, prefill, and decode stages.

Mixture of ExpertsMoEactivated parameters
0 likes · 15 min read
From Dense to MoE: Decoding Total vs. Activated Parameters
Cambridge Mofang Notes
Cambridge Mofang Notes
Mar 13, 2026 · Information Security

OpenClaw Keeps Running After Terminal Close: WSL2 Security Risk & Fix

When running OpenClaw locally via WSL2, closing the terminal window does not stop the gateway service, leaving it accessible on open ports and exposing API keys and local files; the article explains the WSL2 mechanism behind this, provides two proper shutdown methods, and lists four security practices to mitigate the risk.

API Key ExposureLocal DeploymentOpenClaw
0 likes · 3 min read
OpenClaw Keeps Running After Terminal Close: WSL2 Security Risk & Fix