M13T retweeted
We just open-sourced MCode Stack: the actual workflows and skills the MiniMax Code team uses every day to build MiniMax Code.
github.com/MiniMax-AI/mcode-…
M13T retweeted
M3.1 Flash Weight is public now:
Hugging Face:
huggingface.co/MiniMaxAI/Min…
ModelScope:
modelscope.cn/models/MiniMax…
M13T retweeted
MiniMax's latest text model, M3.1-Flash-Preview, debuts today on MiniMax Code.
Built for everyday development, it's fast, reliable, and ready for real work, from quick bug fixes to full features.
M13T retweeted
Replying to @mylifcc
当然MiniMax Code有很多优化空间,但我想在此分享一些事情:
1. 用pi-mono的原因是因为pi的模型网关、Agent Loop、一些底层工具的封装已经非常标准了,没有必要重复造轮子。
2. TUI交互没有刻意去学谁,不过确实看了很多Claude Code的TUI设计交互理念。
3. 关于测评,我要澄清一点,Frontier Harness Eval这个Benchmark评测任何一个Harness用的都是同一个模型,通过控制变量法来进行有效对比。
frontierharness.org/
M13T retweeted
Blender + H3 + MiniMax Code = blockout to final video.
Build the scene. Pose the characters. Move the camera.
Give H3 your blockout video with a prompt or reference image, and watch it come to life with textures, lighting, and detail.
All in MiniMax Code.
M13T retweeted
Replying to @MiniMax_Code
@MiniMaxAgent just shipped H3-based plugins for dynamic images and white-model rendering! Been playing around with them a bit. We're still tuning the white model quality, but this is already pretty fun to mess with~
M13T retweeted
Starting today, we’re opening the MMC TUI invite-only beta 🚀
Bring it into real repos, take on tough engineering tasks, and help us shape a coding agent built for the terminal. We’ll reset usage quotas for all beta participants later this week.
A huge thank you in advance to everyone joining us—we can’t wait to build this with you!
If u want to join our beta testing, please DM @MiniMaxAgent













