Deepseek - DEV Community

DEV Community

#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.
How Open-Source LLMs Differ: Comparing 130+ Model Architectures

How Open-Source LLMs Differ: Comparing 130+ Model Architectures

5
Comments 1
7 min read
Twelve DeepSeek Harness Plugins, Mapped by Failure Surface

Twelve DeepSeek Harness Plugins, Mapped by Failure Surface

Comments
7 min read
DeepSeek dsh-superagent: The AI Teammate That Watches Your GitHub Repo and Answers With Pull Requests

DeepSeek dsh-superagent: The AI Teammate That Watches Your GitHub Repo and Answers With Pull Requests

1
Comments
6 min read
Ataques autĂłnomos con Cairn entran en 10 organizaciones

Ataques autĂłnomos con Cairn entran en 10 organizaciones

Comments
4 min read
TraceScope 0.3.6: USB crash capture for crashes that never reach the APM

TraceScope 0.3.6: USB crash capture for crashes that never reach the APM

2
Comments 2
3 min read
Evaluating DeepSeek-V4.1-Flash-1017 on a 60-Page PDF: What Text Extraction Misses

Evaluating DeepSeek-V4.1-Flash-1017 on a 60-Page PDF: What Text Extraction Misses

Comments
8 min read
DeepSeek Harness Explained: The Open-Source AI Agent Runtime

DeepSeek Harness Explained: The Open-Source AI Agent Runtime

Comments
6 min read
Rekap pemakaian API AI Indonesia, November 2026 (minggu 1–2)

Rekap pemakaian API AI Indonesia, November 2026 (minggu 1–2)

Comments
4 min read
Comparing 7 Chinese frontier models through one API — a field guide, not a benchmark

Comparing 7 Chinese frontier models through one API — a field guide, not a benchmark

Comments
5 min read
DeepSeek: Zuerst die Methode festhalten, dann erst ErgÀnzungen holen

DeepSeek: Zuerst die Methode festhalten, dann erst ErgÀnzungen holen

Comments
8 min read
AgenteDSH de DeepSeek Harness: mi experiencia migrando una app legacy

AgenteDSH de DeepSeek Harness: mi experiencia migrando una app legacy

Comments
4 min read
DeepSeek V4.1 Flash in DeepSeek Harness: GenUI praktisch einrichten und prĂŒfen

DeepSeek V4.1 Flash in DeepSeek Harness: GenUI praktisch einrichten und prĂŒfen

Comments
7 min read
AI gateway benchmark: OpenRouter, Vercel, Ramp, Keln. Comparing cache hit rate, speed, reasoning and cost.

AI gateway benchmark: OpenRouter, Vercel, Ramp, Keln. Comparing cache hit rate, speed, reasoning and cost.

Comments
7 min read
DSH Agent Enhancer 0.3.9: the agent in your DeepSeek Harness desktop can now drive its own browser

DSH Agent Enhancer 0.3.9: the agent in your DeepSeek Harness desktop can now drive its own browser

Comments
4 min read
DeepSeek Flash vs V4 Pro: Which Model Should You Route?

DeepSeek Flash vs V4 Pro: Which Model Should You Route?

Comments
3 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.