WFD Ryu慢来
338 posts
@WFD_ryufps @ni5arga @veelesec A great model with the wrong tooling can feel average. The workflow layer matters.
English
I'm a Gmail user.
Give me ONE reason to switch to Proton.📧
English
To use DeepSeek-V4-Flash-0731 in OpenCode, you need to enable “Enable models hosted in China” in the Control Center.
The 0731 model has not yet been deployed to servers outside China, so OpenCode requires users to explicitly consent to using China-hosted models. Otherwise, requests will fail with a 403 error.
徹言@iamcheyan
DeepSeek 这次刚发布的 Flash 最新版暂时没有部署到海外服务器，所以 OpenCode 要求用户单独同意中国区托管，需要在控制中心里打开 Enable models hosted in China 选项，否则会报403错误。
English
Our goal is to make ChatGPT better as a super assistant wherever you are doing your work!
When you are in Chrome, use our extension that brings the full power of ChatGPT desktop next to where you work.
When you are in the Desktop app, use the in-app browser that makes reviewing and iterating your artifacts much easier and faster.
Today's update brings many of our favorite features from Atlas into both of these surface areas!
ChatGPT@ChatGPT
Good news for anyone with too many tabs: ChatGPT is getting better around the web. 🧩 Chrome extension: In Side Chat, ask about a YouTube video, reference your open tabs, or highlight text on a page and ask away. 💻 Desktop app: Get URL suggestions as you type, revisit your browser history, and choose how it’s managed. Rolling out today.
English
@VijayGajeraO This post is the evidence how lack of knowledge is dangerous for humanity @VijayGajeraO please first educate yourself before making such foolish posts
English
This happens when you get exposed.
Office Of Vijay Patel@VijayGajeraO
So here is the complete picture. It was a Marxist outfit, @internetfreedom, behind these two whistleblowers. They have also published a toolkit for violent protesters. Its founder, Apar, is working very closely with the Marxist outfits. They have received funds from Azim Premji.
English
GLM > Kimi > Deepseek > Qwen > MiniMax > Gemma > Laguna > Nemotron > Nex > MiMo > HY3 > Inkling > GPT-OSS > Ling
My honest opinion having run every single one of these (except inkling which I’ve tried via api)
I would say the top 10 here are going far if they keep publishing
English
T3 Code is the 2nd most popular "developer tool" in the App Store.
...I think this means I'm supposed to raise money, right?
English
I tried the model and it literally overthinks into an infinite loop 💀
Classic issue with reasoning models when they get stuck in their own head trying to deliberate.
Model: inclusionai/ling-3.0-flash:free
Ant Ling@AntLingAGI
Today, we’re releasing Ling-3.0-flash—a hybrid-reasoning MoE model built for production-scale agents. 124B parameters. Just 5.1B active per token. With 1/8 of the total and 1/12 of the active parameters, it matches or beats our 1T flagship model on most benchmarks shown.
English
🚀 Qwythos-27B-v1 is here! The 27B you've been waiting for.
The bigger sibling to Qwythos-9B. Native MTP head intact, full vision tower, still uncensored, still 1M context. Apache-2.0.
huggingface.co/empero-ai/Qwyt…
English
