DeepSeek

DeepSeek V4.1 Flash Released, Now Adapted for Harness

DeepSeek V4.1 Flash is here: a 552B MoE model with faster inference, lower API costs, and full Harness v0.1.5 support for smarter AI agents.

Sep 10 • Meng Li

DeepSeek Harness vs. Codex Harness: A Clash of Engineering Philosophies

Compare DeepSeek Harness and Codex Harness, two competing Agent execution systems. Learn which engineering philosophy fits your AI strategy.

Aug 24 • Meng Li

DeepSeek Multimodal Model deepseek-v4-flash-vision-exp Released

DeepSeek launches vision-enabled V4-Flash multimodal model with Files API, low-cost token pricing, and Agent-ready image understanding.

Aug 22 • Meng Li

DeepSeek Harness: Claude Code & Codex Become Sub-Agents

DeepSeek Harness v0.1.0-rc.8 adds Claude Code & Codex as sub‑agents, multimodal image input, concurrent search, and persistent terminal sessions.

Aug 20 • Meng Li

DeepSeek Harness Plugin Recommendations, Round 2

Discover 8 practical DeepSeek Harness plugins for workflow control, file annotation, browser automation, and custom tool creation. Boost your Agent…

Aug 16 • Meng Li

I Dived Into DeepSeek Harness's 219 Packages

Explore DeepSeek Harness with 219 plugins, Agent runtime, Cordis architecture, session recovery, tool orchestration, and token optimization for AI…

Aug 15 • Meng Li

DeepSeek V4 Pro Released

DeepSeek V4 Pro launches with 1M context, 384K output, low pricing, and Agent focused API support.

Aug 13 • Meng Li

DeepSeek-V4-Flash Official Version Open-Sourced

DeepSeek-V4-Flash Official Version is now open-sourced with post-training breakthroughs, 304B parameters, and efficient GGUF quantization for affordable…

Aug 2 • Meng Li

DeepSeek V4 Flash + Codex: Too Fast for Cheap

Try DeepSeek V4 Flash via Codex for ultra-fast Agent performance at just ¥1 per million tokens—budget price, Pro-level work.

Aug 1 • Meng Li

DeepSeek V4 "Full-Blooded Version" Revealed!

DeepSeek V4 official launch imminent with Pro and Flash versions. Early gray scale tests reveal lower pricing, peak valley billing, and strong…

Jul 19 • Meng Li

DeepSeek Plans to Launch IPO This Year!

DeepSeek IPO news, Liang Wenfeng net worth surge to 36 billion, and second fundraising round at 480 billion valuation. AI model market shifts.

Jul 15 • Meng Li

DeepSeek V4 Also Supports Multimodal in Claude Code

Fast, cheap, and smart DeepSeek V4 now works in Claude Code with images via a free local vision tool. No multimodal needed.

May 28 • Meng Li

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts