#DeepSeek reverse engineering
120 related articles
·4 min
RAM: First-Principles Approach to 50x Faster RL Post-Training for Diffusion Models
RAM (Reinforce Adjoint Matching) achieves 50x faster RL post-training for diffusion models by discarding path costs, combining ODE sampling with decorrelated training objectives. A deep dive into RAM's core principles and experiments vs. Flow-GRPO.
Read more →
·4 min
Claude Code in China: Model Selection & Cost-Saving Configuration Guide
How can Chinese developers access Claude Code affordably? This guide covers model selection (DeepSeek V4 Pro top pick), proxy vs. direct connection risks, environment variable setup, and Coding Plan cost-saving strategies.
Read more →
·3 min
Anthropic's Project Glass Wing: The Arms Race in AI Code Security Auditing
Anthropic launches Project Glass Wing—its Mythos Preview model found over 10,000 critical infrastructure vulnerabilities in hours, spanning 150 organizations across 15 countries. A deep dive into AI security auditing.
Read more →
·3 min
The Rise of Diffusion Language Models: DiffusionGemma Crushes Autoregressive Models in Speed Tests
Diffusion language model DiffusionGemma dramatically outpaces autoregressive Deepseek Flash in speed tests. Explore the tech behind diffusion vs. autoregressive models and their challenges.
Read more →
·4 min
The Claude Code Covert Tagging Scandal: The AI Trust Crisis Behind Alibaba's Ban
Anthropic's Claude Code is accused of covert tagging via Unicode punctuation encoding, prompting Alibaba to ban its use. A deep dive into the reverse-engineering findings, distillation allegations, and the AI-era battle over compute monopoly and developers' right to know.
Read more →
·5 min
Hands-On with PageAgent: Add AI Agent Capabilities to Web Pages with a Single Line of Code
In-depth hands-on review of Alibaba's open-source web automation tool PageAgent: three integration methods, script execution analysis, and a full breakdown of current limitations. Add AI Agent capabilities to web pages with one line of JS.
Read more →
·5 min
Building DeepSeek Agents and Knowledge Bases from Scratch: A Practical Guide to Commercial Deployment
A systematic guide to the full DeepSeek Agent development process: covering prompt engineering, the ReAct framework, workflow orchestration, local deployment, and business requirement breakdown for commercial-ready AI Agents.
Read more →
·7 min
GPT-5.6 and Grok 4.5 Launch Simultaneously, Meta Unveils Agent-Based Image Model
OpenAI GPT-5.6 expands its preview, xAI Grok 4.5 opens access at the same time, Meta releases the Agent-based Muse Image model and Muse Video model, while Apple and DeepSeek launch in-house AI inference chip programs. A quick look at the week's five biggest AI stories.
Read more →
·5 min
Alibaba Bans Claude Code: Invisible Fingerprints and the AI Tool Trust Crisis
Alibaba has banned Claude Code as high-risk software. Reverse engineering revealed a covert environment-identification mechanism hiding user fingerprints in punctuation via prompt steganography. A deep dive into the incident and AI tool trust.
Read more →
·6 min
OpenAI Releases GPT-5.6: Cybersecurity Capabilities Take Center Stage
OpenAI launches the GPT-5.6 model family with cybersecurity as its biggest highlight. A deep analysis of GPT-5.6's differentiation, double-edged-sword effect, and enterprise strategy.
Read more →
·6 min
The Complete Beginner's Guide to Claude Code: From Installation to Advanced Usage
Claude Code is one of the most powerful AI coding agents, running in the terminal to write code, batch operations, build web projects, and more. This guide covers installation, connecting local models via CC Switch, permission modes, CLAUDE.md, Skills, MCP, Subagents, and more.
Read more →
·6 min
Grok 4.5 Deep Dive: Coding on Par with Top Models, at a Fraction of the Cost
A senior developer's 24-hour deep test of Grok 4.5: a 1.5T-param MoE model at $2/M input tokens, with coding benchmarks rivaling GPT-5.5. Real performance, token efficiency, and limits explained.
Read more →
·6 min
Introduction to Prompt Engineering: Principles, Methods, and Practical Case Studies
Prompt Engineering is the core skill for harnessing LLMs. This article covers principles and design methods through real cases like translation role-setting and DeepSeek image generation.
Read more →
·7 min
GLM-5.2 Released: Open-Source Coding Capability Approaches Closed-Source Flagships for the First Time
GLM-5.2 tops open-weight models in coding with a 74.4 Frontiers-WE score, beating GPT-5.5. Its MIT license enables local deployment, and the gap with closed-source flagships is closing fast.
Read more →
·3 min
Alibaba's Claude Ban Explained: The Truth Behind Three Converging Timelines
Alibaba banned Claude company-wide, flagging Claude Code as high-risk. Three converging timelines — Anthropic's distillation attack allegations, the 1260H list, and Claude Code's hidden detection system — reveal the geopolitical logic behind the ban.
Read more →
·3 min
How Alibaba Banned Claude: A Complete Breakdown of the Three Hidden Detection Layers
Claude Code was found to contain three covert detection layers: Chinese timezone checks, steganographic prompt marking, and identity fingerprints sent with every request. Alibaba banned all Claude products, forcing ~20,000 engineers to switch tools.
Read more →
·6 min
Unsloth Major Update: DeepSeek-V4 Support and a Deep Dive into NVFP4 Quantized Export
Unsloth v0.1.481-beta adds full DeepSeek-V4-Flash support, NVFP4/FP8/imatrix GGUF quantized export, 1.3x faster GRPO, 3-5x faster MoE training, and an OpenAI-compatible API service in Studio.
Read more →
·7 min
Getting Started with Dify: A Complete Guide from Local Deployment to Building Enterprise-Grade AI Applications
A detailed guide to Dify, the open-source LLM app development platform, covering its core features and full local deployment via VMware + Ubuntu + aaPanel + Docker. Supports 100+ models like DeepSeek and ChatGPT to build enterprise AI apps fast.
Read more →
·7 min
GPT-5.6 Sol vs. Fable 5: Can Half the Price Match the Flagship?
OpenAI launches GPT-5.6 Sol at half the price of Anthropic's Fable 5. We compare both models on HealthBench, cybersecurity and more using hard system-card data, analyzing Sol's cost-effectiveness and shifts in AI power.
Read more →
·7 min
A Complete Guide to LangGraph's Core Concepts: The Framework of Choice for Enterprise Agent Development
An in-depth analysis of LangGraph's core concepts: short-term and long-term storage mechanisms, its differences from LangChain, the MIT open-source license, and private deployment solutions for enterprise Agent development.
Read more →