FRAMEWIREIndonesiaUpdated Nov 8Live wire
0:00 / 0:00

DeepSeek Harness official is a bit interesting this time, they directly made all 7 sets of plug-in development prompts public🔥

When we see a good plug-in before, our first reaction may be to go to GitHub to find the source code. But this time is different. DeepSeek officially compiled the prompt words used in the demonstration video, both in Chinese and English. From 3D visualizations to video clips and even paper readers, just use Creator…

小墨同学Nov 84
0:00 / 0:00

The whole AI race is 2 countries.

America has ChatGPT. America has Claude. America has Gemini. America has Grok. America has Llama. America has Muse. China has DeepSeek. China has Qwen. China has Kimi. China has GLM. China has Hunyuan. So what do I have?

🇦🇪 Rashid Al Mansoori راشد المنصوريNov 88
0:00 / 0:00

The 9B model learns V4 Pro reasoning, and there are only 3 answers left.

The 9B model learns V4 Pro reasoning, and there are only 3 answers left. A 9B model that has been very popular recently on Hugging Face: DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic. After reading the model card, I compiled some of its highlights👇 1️⃣ What is The base is Qwen3.5-9B.

LinXunFengNov 81
0:00 / 0:00

Deepseeks version. I love Deepseek and other models but Opus 5.5 is definitely magic on things like this.

I made it as fair as I could and this was the 3rd try as well.

Loktar 🇺🇸Nov 87