用户实测 OpenAI Dots：界面好评但工具连接与任务执行问题多
这位博主天天用 OpenAI 模型，他把 Dots 的毛病一条条列出来了：工具连不上、忘任务清单，还说 Grok Bot 干活更利索。
一位日常使用 OpenAI 模型数小时的用户评测了 Dots，认为其 UI 达到了理想形态，但底层系统问题频出。他列举了连接工具时报错不断、会话管理混乱、任务清单经常被遗忘等问题。他猜测 Dots 的架构是通过 dot 会话到云端会话再回到本地会话通信，链路过于复杂。他建议 OpenAI 把 work、chat 和 Codex 合并，让 Dots 直接复用 ChatGPT 会话，并认为 Grok Bot 在多智能体管理和实际完成任务方面明显更胜一筹。
OpenAI's Dots has huge potential, the model seems good, the UI is what AI should be, but the system behind it is awful. It's just not ready yet. They need to get on this and fix these issues ASAP. The errors with connecting to tools, sessions, etc., are endless. The amount of work it gets done is tiny. It forgets it's task list. There's virtually zero proactiveness from it. It doesn't seem to act like it's an orchestrator. It' doesn't seem to have the right mindset. It seems to use a dot session to communicate to a cloud session that then communicates to a local session then back the other way, which seems very convoluted. It's just very broken.
OpenAI, I've asked many times now to be added to your trusted tester programme. I'd love to help you fix your models, apps, tools and systems. If only in a tiny way. I use your models for hours every single day. I need these things to work (much like I need Copilot to work for work, much like I need Google Gemini to work outside of work).
Can you please merge work, chat, and Codex into one and have Dots use ChatGPT sessions rather than its own Dots sessions?
Grok Bot is still way ahead and just gets things done. It manages multiple agents so much better.
