Forem

# deepseek

DeepSeek is a Chinese artificial intelligence company that has developed an open-source AI model, DeepSeek-R1, which rivals leading models like OpenAI's o1 in performance, yet was created in under two months at a cost of less than $6 million, significantly lower than its competitors.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
2025 Major Release: How Does DeepSeekMath-V2 Achieve Self-Verifying Mathematical Reasoning? Complete Technical Analysis

2025 Major Release: How Does DeepSeekMath-V2 Achieve Self-Verifying Mathematical Reasoning? Complete Technical Analysis

1
Comments
6 min read
Why Silicon Valley Is Quietly Migrating to Chinese AI Models

Why Silicon Valley Is Quietly Migrating to Chinese AI Models

4
Comments 2
10 min read
How To Use DeepSeek-OCR And Docling For PDF Parsing
Cover image for How To Use DeepSeek-OCR And Docling For PDF Parsing

How To Use DeepSeek-OCR And Docling For PDF Parsing

Comments
7 min read
DeepSeek OCR in Automation Pipelines: Practical Engineering Insights and Integration Patterns
Cover image for DeepSeek OCR in Automation Pipelines: Practical Engineering Insights and Integration Patterns

DeepSeek OCR in Automation Pipelines: Practical Engineering Insights and Integration Patterns

32
Comments 8
4 min read
DeepSeek-OCR: The New 'Black Tech' in AI, How It's Changing Our Interaction with AI Models?
Cover image for DeepSeek-OCR: The New 'Black Tech' in AI, How It's Changing Our Interaction with AI Models?

DeepSeek-OCR: The New 'Black Tech' in AI, How It's Changing Our Interaction with AI Models?

Comments
5 min read
a introduction to deepseek API

a introduction to deepseek API

Comments
3 min read
Paddle OCR-VL & DeepSeek-OCR

Paddle OCR-VL & DeepSeek-OCR

Comments
2 min read
AIReview in Practice: Accelerating Code Reviews with AI

AIReview in Practice: Accelerating Code Reviews with AI

Comments
4 min read
DeepSeek Does It Again: From MoE to DSA, The New Era of LLM Efficiency
Cover image for DeepSeek Does It Again: From MoE to DSA, The New Era of LLM Efficiency

DeepSeek Does It Again: From MoE to DSA, The New Era of LLM Efficiency

Comments
4 min read
Exploring the Technical Advantages of Rust Language in High-Performance AI Applications
Cover image for Exploring the Technical Advantages of Rust Language in High-Performance AI Applications

Exploring the Technical Advantages of Rust Language in High-Performance AI Applications

Comments
7 min read
DeepSeek-OCR: When a Picture Is Actually Worth 10 Fewer Tokens
Cover image for DeepSeek-OCR: When a Picture Is Actually Worth 10 Fewer Tokens

DeepSeek-OCR: When a Picture Is Actually Worth 10 Fewer Tokens

7
Comments
9 min read
OpenAI Hits $500B While China Cuts AI Costs in Half

OpenAI Hits $500B While China Cuts AI Costs in Half

1
Comments
3 min read
Cost-Controllable AI Applications: Litho's Cache Optimization and Cost Control Strategies

Cost-Controllable AI Applications: Litho's Cache Optimization and Cost Control Strategies

Comments
7 min read
Book review: “Build a DeepSeek Model (From Scratch)”

Book review: “Build a DeepSeek Model (From Scratch)”

1
Comments
12 min read
Litho: Let Code Speak for Itself - The AI-Driven Revolution in Automated Architecture Documentation Generation

Litho: Let Code Speak for Itself - The AI-Driven Revolution in Automated Architecture Documentation Generation

Comments
7 min read
In-depth Analysis of Litho's Multi-Agent Collaborative Architecture and ReAct Reasoning Mechanism
Cover image for In-depth Analysis of Litho's Multi-Agent Collaborative Architecture and ReAct Reasoning Mechanism

In-depth Analysis of Litho's Multi-Agent Collaborative Architecture and ReAct Reasoning Mechanism

1
Comments
9 min read
Researching Litho's Intelligent Caching and Performance Optimization Strategies

Researching Litho's Intelligent Caching and Performance Optimization Strategies

Comments
6 min read
Complete Guide 2025: How DeepSeek OCR Reduces AI Costs by 20x Through "Visual Compression"

Complete Guide 2025: How DeepSeek OCR Reduces AI Costs by 20x Through "Visual Compression"

1
Comments
10 min read
Litho Project Architecture Analysis: How the Four-Stage Pipeline Enables Automated Documentation Generation

Litho Project Architecture Analysis: How the Four-Stage Pipeline Enables Automated Documentation Generation

Comments
8 min read
DeepSeek-V3.2-Exp Complete Analysis: 2025 AI Model Breakthrough and In-Depth Analysis of Sparse Attention Technology

DeepSeek-V3.2-Exp Complete Analysis: 2025 AI Model Breakthrough and In-Depth Analysis of Sparse Attention Technology

Comments
7 min read
Giving DeepSeek a Spin for Bookmark Organization

Giving DeepSeek a Spin for Bookmark Organization

4
Comments
2 min read
How i struggle with exporting DeepSeek to PDF and make my own solution
Cover image for How i struggle with exporting DeepSeek to PDF and make my own solution

How i struggle with exporting DeepSeek to PDF and make my own solution

Comments
2 min read
DeepSeek R1: The $5.6M AI That Just Destroyed Silicon Valley
Cover image for DeepSeek R1: The $5.6M AI That Just Destroyed Silicon Valley

DeepSeek R1: The $5.6M AI That Just Destroyed Silicon Valley

32
Comments
2 min read
DeepSeek V3.1 Meets Promptfoo: Jailbreaks, Biases & Beyond
Cover image for DeepSeek V3.1 Meets Promptfoo: Jailbreaks, Biases & Beyond

DeepSeek V3.1 Meets Promptfoo: Jailbreaks, Biases & Beyond

5
Comments
15 min read
The Great AI Battle of 2025: OpenAI vs DeepSeek vs Qwen - Who's Actually Winning?
Cover image for The Great AI Battle of 2025: OpenAI vs DeepSeek vs Qwen - Who's Actually Winning?

The Great AI Battle of 2025: OpenAI vs DeepSeek vs Qwen - Who's Actually Winning?

23
Comments
4 min read
loading...