Dot 该不该有多个版本？作者主张一人一个就够
Dot 用户在吵要不要多个 Dot，作者说一个就够，子智能体干活就行，理由挺有参考价值。
围绕个人助理产品 Dot，社区不少人请求推出多个 Dot 实例。作者认为 Dot 应该只保留一个，通过调用子智能体来扩展能力，而不是让用户开多个。他担心多 Dot 会重回当前智能体产品“多会话、多模式、多推理档位”的混乱状态，并称自己已把每家 AI 的会话削减到一个。作者还预期硬件上市后，用户不会愿意同时和多个个人助理对话。
I see lots of people asking for multiple Dots. I get it, but also don't. For me, it should just be one. I get that the Dot should be calling on sub-agents (sub-Dots?), but why would you want more than one? This is your personal assistant.
I think having more than one will just confuse normies again. Sure they could just ignore it, but it's just too many options for most people. That would be going back to what we already have: a confusing mess of agents, sessions, modes, models and reasoning levels.
When the hardware arrives, no one's going to want to talk to multiple personal assistants. I've already cut my sessions back to one per AI.
I'm curious on your thoughts, though: what would you do with many Dots? 🤔
