Fangyin Cheng

eosphoros-ai 社区核心成员。Lead DB-GPT.

[Kimi.ai @Kimi_Moonshot]

Releasing the model weights and technical report of Kimi K3.

Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window.

New model architecture: 2.5x the intelligence per unit of compute, not just more params.

Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale.

Model weights: https://t.co/7m7eEg6Y0B
Tech report: https://t.co/yeu6cjpMCT
Tech blog: https://t.co/YTfiMSNM1f

[Fangyin Cheng @staneyffer]

@9hills 我的经验是分成三类测试，第一类是单测，AI 自己写，第二类是端到端测试，尽可能包含外界环境，第三类是要求 AI 给开发者写的手动测试脚本，将端到端测试分成几个手动执行的步骤，方便开发者执行验证和理解整个过程。

[Fangyin Cheng @staneyffer]

❤️❤️❤️

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length.

🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models.
🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice.

Try it now at https://t.co/GCdiMzk1Dl via Expert Mode / Instant Mode. API is updated & available today!

📄 Tech Report: https://t.co/drlDrxkYtp
🤗 Open Weights: https://t.co/T13Y8i7SDM

1/n

[Z.ai @Zai_org]

Introducing GLM-5.1: The Next Level of Open Source

- Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo.
- Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations.

Blog: https://t.co/hmyDe4Nel3
Weights: https://t.co/CuUjXcPKJD
API: https://t.co/fz6reja4fb
Coding Plan: https://t.co/Nk8Y98HNhU

Coming to https://t.co/WCqWT0qCQb in the next few days.

[DeepSeek @deepseek_ai]

🚀 Launching DeepSeek-V3.2 & DeepSeek-V3.2-Speciale — Reasoning-first models built for agents!

🔹 DeepSeek-V3.2: Official successor to V3.2-Exp. Now live on App, Web & API.
🔹 DeepSeek-V3.2-Speciale: Pushing the boundaries of reasoning capabilities. API-only for now.

📄 Tech report: https://t.co/7EyydyNuG0

1/n

[Fangyin Cheng @staneyffer]

一个部门数据没了

[Fangyin Cheng @staneyffer]

@laogui 小模型也有需求，特别是多模态模型

[Fangyin Cheng @staneyffer]

MoonBit 的语法设计深得我心，异步库 async 的开发进展也很快，其中异步运行时的实现非常优雅，目前代码量也不大，学习到了不少东西，也小小提了个支持 IPV6 的 PR https://t.co/VZBlXMSqNZ 。之前计划用 MoonBit 来实现 AI Agent，奈何得从 socket 库造起，以后基于这个异步库来实现工作量小了很多。

[Fangyin Cheng @staneyffer]

@yetone 最近北京的天气确实很舒服！

[Fangyin Cheng @staneyffer]

@yetone 也有额度限制的，一个月不够用几次，之前写过一个类似的 copilot 转 API 的工具，感觉不太好就没公开发布了，哈哈

[Fangyin Cheng @staneyffer]

@lemonhxmoe 这个性能与Python无关😅

[Qwen @Alibaba_Qwen]

>>> Qwen3-Coder is here! ✅

We’re releasing Qwen3-Coder-480B-A35B-Instruct, our most powerful open agentic code model to date. This 480B-parameter Mixture-of-Experts model (35B active) natively supports 256K context and scales to 1M context with extrapolation. It achieves top-tier performance across multiple agentic coding benchmarks among open models, including SWE-bench-Verified!!! 🚀

Alongside the model, we're also open-sourcing a command-line tool for agentic coding: Qwen Code. Forked from Gemini Code, it includes custom prompts and function call protocols to fully unlock Qwen3-Coder’s capabilities. Qwen3-Coder works seamlessly with the community’s best developer tools. As a foundation model, we hope it can be used anywhere across the digital world — Agentic Coding in the World!

💬 Chat: https://t.co/V7RmqMaVNZ
📚 Blog: https://t.co/syL1hsSGKq
🤗 Model: https://t.co/1LWwUKMrBN
🤖 Qwen Code: https://t.co/qqwj5nAO3Z

[Fangyin Cheng @staneyffer]

最近一直在想如何优雅地在 MoonBit 中释放资源，终于让我在官方异步库中找到了！
derfer 算是 Go 中为数不多的我喜欢的设计了。

[Fangyin Cheng @staneyffer]

@yetone 这么巧！刚提完 PR ，准备去上班。

[Fangyin Cheng @staneyffer]

@yetone 今天起床发现电脑已经死活开不了机了，尽管没升级也没动啥，更惨的是半年没做系统快照了😅😅

[Fangyin Cheng @staneyffer]

@yetone 每次升级都必须保证时间机器快照备份完成，之前挂过几次很折磨。

[Qwen @Alibaba_Qwen]

Introducing Qwen3!

We release and open-weight Qwen3, our latest large language models, including 2 MoE models and 6 dense models, ranging from 0.6B to 235B. Our flagship model, Qwen3-235B-A22B, achieves competitive results in benchmark evaluations of coding, math, general capabilities, etc., when compared to other top-tier models such as DeepSeek-R1, o1, o3-mini, Grok-3, and Gemini-2.5-Pro. Additionally, the small MoE model, Qwen3-30B-A3B, outcompetes QwQ-32B with 10 times of activated parameters, and even a tiny model like Qwen3-4B can rival the performance of Qwen2.5-72B-Instruct.

For more information, feel free to try them out in Qwen Chat Web (https://t.co/bg4tAU1p74) and APP and visit our GitHub, HF, ModelScope, etc.

Blog: https://t.co/Z8YgHerTXz
GitHub: https://t.co/Ij0Vne5b5K
Hugging Face: https://t.co/V1WxhQ0fad
ModelScope: https://t.co/Z9Z37FODVN

The post-trained models, such as Qwen3-30B-A3B, along with their pre-trained counterparts (e.g., Qwen3-30B-A3B-Base), are now available on platforms like Hugging Face, ModelScope, and Kaggle. For deployment, we recommend using frameworks like SGLang and vLLM. For local usage, tools such as Ollama, LMStudio, MLX, llama.cpp, and KTransformers are highly recommended. These options ensure that users can easily integrate Qwen3 into their workflows, whether in research, development, or production environments.

Hope you enjoy our new models!

[Fangyin Cheng @staneyffer]

❤️❤️❤️

[DeepSeek @deepseek_ai]

🚀 DeepSeek-V3-0324 is out now!

🔹 Major boost in reasoning performance
🔹 Stronger front-end development skills
🔹 Smarter tool-use capabilities

✅ For non-complex reasoning tasks, we recommend using V3 — just turn off “DeepThink”
🔌 API usage remains unchanged
📜 Models are now released under the MIT License, just like DeepSeek-R1!
🔗 Open-source weights: https://t.co/DmaMLhfngk

[Fangyin Cheng @staneyffer]

DeepSeek-V3-0324 代码能力很不错，相信没多久 DeepSeek 应该就能替代 Cluade 3.7 Sonnet了。
2048 游戏、动态天气应用、SVG 架构图以及李继刚周报prompts，效果都很惊艳。

DB-GPT 中使用：

https://t.co/iAix2owQml

[Fangyin Cheng @staneyffer]

DB-GPT v0.7.0 终于来了，架构上逐步接近我理想中的样子了！
MCP + Multi-Agent、DeepSeek R1 等推理模型的支持和场景优化、GraphRAG 检索链路增强以及架构全面升级。
20 + 功能增强项、40+ bug fix、20+ 其它内容...

English release blog:
https://t.co/EukAfIu6So