#DeepSeek
351 related articles
Getting Started with DeepSeek Harness: A Complete Guide to Node.js Installation and Configuration
Beginner's guide to DeepSeek Harness: install Node.js on Windows, configure npm directories, and set system environment variables — avoiding common C drive and path issues.
DeepSeek V5 Leaked: Open-Source Model Takes Aim at Astra as Multi-Front Model Battle Looms
DeepSeek V5 leaked targeting GPT-6 Astra, Kimi K3.1 and Anthropic Opus 5.5 also incoming. A breakdown of the latest AI model leaks and the intensifying race.
DeepSeek V4.1 Flash: 5-Day Real-World Test — The Problem Isn't the Model, It's How You're Using It
5-day DeepSeek V4.1 Flash real-world test: 250 tokens/sec speed, but vastly different experiences across Harnesses. How context pollution and workflow matching explain everything.
Dissecting DeepSeek V3: Four Engineering Secrets Behind Training a 671B Model for $5.576M
A line-by-line breakdown of the DeepSeek V3 technical report reveals four engineering decisions — MoE routing, auxiliary-loss-free balancing, MLA attention compression, and FP8 mixed-precision training — behind training a 671B model for $5.576M.
DeepSeek V4.1 Flash Deep Dive: The Architectural Revolution Behind Its Rock-Bottom Pricing
DeepSeek V4.1 Flash: How CED architecture, CSA2 sparse attention, and FP4 caching compress KV Cache by 437x, cut costs 60%, and beat expensive flagships on agentic benchmarks.
DeepSeek V4.1 Flash Hands-On: 65 Million Tokens Burned for Under $1
DeepSeek V4.1 Flash: 65M tokens in 89 minutes for under $1. Deep dive into its CED architecture, sub-1KB KV cache, Ingram conditional memory, and MIT license.
DeepSeek Harness Goes Open Source: An AI Agent Foundation Where Everything Is a Plugin
DeepSeek Harness is now open source. Built on an "everything is a plugin" philosophy, it supports 20+ LLM providers and launches a local Web UI with a single command.
What Are APIs and API Keys? A 4-Minute Explainer Using DeepSeek's Docs
What are APIs and API Keys? Using DeepSeek's official docs and a live terminal demo, this guide explains the core concepts in 4 minutes with a simple door-and-key analogy.
Building a RAG Knowledge Base Q&A System from Scratch: A Full Walkthrough with DeepSeek Integration
Build a RAG private knowledge base Q&A system from scratch with Python and DeepSeek. Learn document upload, vector indexing, and retrieval-augmented generation.
Claude Code Complete Setup Guide: Connecting to Chinese AI Models Step by Step
Step-by-step Claude Code setup guide for Chinese users: configure Node.js, bypass login, connect DeepSeek via CCSwitch, and boost code quality with Superpowers TDD plugin.
DeepSeek Harness Penetration Testing Mode in Practice: Capabilities and Boundaries of AI-Assisted Vulnerability Hunting
A hands-on look at AI-assisted vulnerability hunting using DeepSeek Harness with a dedicated SKILLS package, covering recon, WebShell backdoors, RCE, and database credential leaks.
Overseas Blogger Tests DeepSeek's New Flash Model: KV Cache Efficiency Up 337x
Overseas blogger benchmarks DeepSeek's new Flash model: 337x KV cache efficiency gain, native AutoML, object detection, and visual generation — full hands-on breakdown.
DeepSeek's Voice Goes Viral: Where Does That "Imperial Officer Accent" in Chinese-Japanese Mixed Reading Come From?
DeepSeek's TTS produces a quirky 'Imperial Officer accent' on Chinese-Japanese mixed text. We break down the prosodic and language-identification mechanics behind this viral phenomenon.
DeepSeek UI: An Open-Source Browser Extension That Supercharges the DeepSeek Web Experience
DeepSeek UI is an open-source browser extension for Edge and Chrome that adds keyword highlighting, one-click quoting, Markdown/HTML export, and auto-collapse thinking to DeepSeek's web interface.
A DeepSeek Researcher's Confession: The AI He Trained Is About to Replace Him
DeepSeek V4.1 kernel engineer Liu Shengyu admits the AI he trained will surpass his own skills within a year—yet he keeps pushing forward. Here's why.
DeepSeek Harness One-Month Retrospective: Highlights, Risks, and the Road Ahead
DeepSeek Harness one-month retrospective: Plugin ecosystem, Codex Kernel, supply chain risks, talent strategy, and the cloud Agent path ahead.
Open-Source Project Tested: Integrating DeepSeek and Other AI Models into WPS via API
An open-source project uses DSL to integrate DeepSeek and other AI models into WPS, enabling in-document generation and revision. ~8,000 tokens per 2,000 characters. Requires a paid API key.
DeepSeek V4.1 Flash Deep Dive: How an Encoder Architecture Slashes Inference Costs to Pennies
DeepSeek V4.1 Flash uses a hybrid encoder architecture to cut inference costs to ~$0.27/task. Deep dive into its 40-layer design, KV cache optimization, benchmark results, plus OpenAI's Navier-Stokes breakthrough controversy, Anthropic's slowdown call, and Mistral's record funding.
Build an AI Agent with Memory from Scratch: Full-Stack with Python, Flask, and DeepSeek
Learn how to build an AI Agent with persistent memory using Python, Flask, and DeepSeek API. Covers selective storage, on-demand recall, and cross-session memory.
Complete Guide: Local Deployment of Personal Knowledge Base with DeepSeek + RAGFlow
Step-by-step guide to deploying DeepSeek locally with Ollama and building a personal knowledge base using RAGFlow on Docker. Covers RAG, Embedding, and full setup.