AI 摘要
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。
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?" → @MiniM...