dots vs. other personal agents: inside ChatGPT is its edge, but the app experience lags
The author argues dots' biggest advantage is living inside ChatGPT with Astra and memory behind it, but cramming Codex, Work and dots into ChatGPT makes it hard for ordinary users to get started.
Here's my take on OpenAI dots vs. the other personal agents: 1. These are really two separate races. dots and Grok Bot are going after work tasks. Muse is going after personal tasks. So I don't think dots competes directly with Muse. 2. Dots' biggest advantage is that it lives inside ChatGPT. My onboarding was seamless because everything was already connected. And with my ChatGPT memory and Astra behind it, it answers big questions like "What should I do to grow my business?" better than other agents. 3. I also think of dots as ChatGPT's official chief of staff agent. My favorite way to use it is to call it on a walk, ask "What should I take care of today?", then have it hand work off to my other ChatGPT threads. 4. In contrast, chatting with my dot in the app is a worse experience. Since it's juggling several tasks at once, it's hard to tell which one it's responding to. I prefer Grok Bot (where each bot works on one thing at a time) or talking to my dot in Slack (which has more obvious conversation threading). 5. I'm a broken record about this, but cramming Codex, Work, dots, Spaces, Pages, and more all into ChatGPT is overwhelming. My hunch is everyone at OpenAI is agent-pilled, so it's hard to take a step back and think about how casual users will learn all this stuff. This is the biggest gap imo - OpenAI needs to think a lot harder about onboarding for normal users. My mom will have no idea how to use any of this. 📌 I talk more about all this in my full dots review and tutorial here: https://youtu.be/z5X1eMU6isI
This post quotes another post: “Video tests OpenAI dots against Grok Bot and Muse”