MiniMax (official)· @MiniMax_AI · X·· 2026-06-17AI 评分43
AI 导读
MiniMax 展示了其 M3 模型在真实 Agent 循环中的应用，通过 Together Compute 提供完整模型栈：Parakeet 负责语音转文字（STT）、MiniMax Speech 2.8 负责语音合成、MiniMax M3 负责推理。Demo 为一个 Mac 顶栏应用，用户提问后 M3 读取屏幕指出薄弱环节，再通过指令直接编辑磁盘上的文件。切换 STT 至 Together AI 后，延迟从 546ms 降至 277ms。
正文 · 原文
nice example of M3 in a real agent loop, all served through @togethercompute
forked clicky into a tiny Mac top-bar app that reviews my website designs, talks back, and patches the code itself. the loop: “what’s wrong with this?” → @MiniMax_AI M3 reads the screen + points at the weak parts “fix it” → it edits the actual files on disk @togethercompute served the full model stack for the demo: Parakeet for STT, MiniMax Speech 2.8 for voice, and MiniMax M3 for reasoning. Even saw a reduction in latency from 546ms to 277ms when switching STT to Together AI demo below在 X 查看被引用的帖子
来源：MiniMax (official) · x.com