Ask HN: What do you do while ChatGPT-5 is thinking?

I use ChatGPT-5 Thinking a lot for day-to-day work. I prefer the response quality over speed, so I always pick the longer-thinking model. It takes ~1–5 minutes (often 1–2) to respond, but those short waits are getting increasingly distracting.

I find myself doing something else, and it eventually takes more than the thinking time. Such as right now, it takes me 5 minutes to write this post, and ChatGPT responded like 3 minutes ago.

Does anyone else have the same problem? What do you do during these gaps? :D

9 points | by cuber_messenger 8 hours ago

12 comments

  • aitchnyu 1 hour ago
    Aider can generate sounds and notifications after it complete its output. Not that it makes me more disciplined. Still waiting for LLMs with ultra fast output.
    [-]
    • fragmede 1 hour ago
      Lets see if any of the text diffusion models ever hit prod. The Gemini Diffusion demo is impressive!
  • chainofthought 8 hours ago
    I'm always prompting. I let Gemini calendar my time (Google Calendar, of course) so that there are zero gaps where unwanted human thought could sneak in. I use an agent manager called Pelican to check in with all of my agents every second and have them tell me what I should be working on next using meta-agents, which are agents running tools in a loop to run tools in a loop. It's super effective!
    [-]
    • iamflimflam1 4 hours ago
      I can’t tell if this is a serious post or not…
      [-]
      • vman512 2 hours ago
        That's my secret Captain, I'm always prompting
  • al_borland 3 hours ago
    I stare are the prompt impatiently, thinking to myself how annoying the wait is and how it used to be faster.
  • eugene-kim 1 hour ago
    When using codex-cli / Claude Code, I look for opportunities to improve either the AGENTS.md file based on the path that the LLM is taking or to improve repo structure, docs, var names, etc that might help make things more clear in the future. Since this is still somewhat task related, I can usually stay focused.

    I haven't had much luck doing two completely different tasks at the same time. At net I think it slows me down due to the context switching.

  • jf22 2 hours ago
    If I can context switch between two prompts I will.

    If the task is hard and I can't easily break context I'll do exercises, chores, or comment on HN.

  • maremmano 1 hour ago
    Obviously I move the mouse pointer so as not to freeze the machine and speed up the process.
  • loveparade 8 hours ago
    I often use that time to spec out a future task. Either by going through Github issues, doing some research and adding details, or by spinning up another codex/claude session to create a detailed design document for a future task and iterating on that. So one agent is coding while another is helping me to spec out future work. So when the coding agent is done I can immediately start on the next task with a proper spec, reducing margin for error.
    [-]
  • dotancohen 5 hours ago
    Anki. Or pushups.

    Anki and AnkiDroid are perfect for filling in those few minutes throughout the day. And if you're in a private environment, a small set of pushups a few times a day keep you awake and make you feel great.

    [-]
    • absoluteunit1 2 hours ago
      Oh this is actually a good idea!

      I’m a heavy Anki user but haven’t considered doing Anki while waiting on LLM responses.

      Disclaimer: I’m also the creator of https://www.raycast.com/anton-suprun/anki

      (Made it to make studying Anki cards and adding cards more convenient and more keyboard friendly)

      [-]
      • dotancohen 2 hours ago
        Raycast is a desktop AI agent?

        I see that your extension supports specific Anki note types. I really heavily on custom note types. Is there an interface to add support for custom note types? Does it run on Linux?

        [-]
        • absoluteunit1 2 hours ago
          > Raycast is a desktop AI agent

          No - it is a MacOS launcher app. This Spotlight but with quite a few more features and very extensible (especially if you code) and has a large open source extension community (mine is just one of many)

          > does it run on Linux?

          Sadly no, only Mac for now but I think they’re expanding to Windows and Linux on future.

          > custom note types

          Not really sadly :/

          I want to add many improvements including this but I don’t have capacity right now - hands full with another project

          [-]
          • dotancohen 1 hour ago
            Thank you, Mac launchers are always interesting. That seems to be a big field.

            As soon as I find a good desktop AI agent for Linux, I think I'll take a shot a writing an Anki MCP server.

    • jorisboris 4 hours ago
      the pushups are a great idea
  • cantouch 7 hours ago
    Use Black Screen app (https://blackscreen1.com/) to stare at the backness of all your monitors. Or look at some random photos with it. :-)
  • pols45 7 hours ago
    I cut and paste the chats into other GPTs to see what they have to say.
  • johnwheeler 2 hours ago
    This is a timely and interesting topic, I was just thinking about this the other day. What I've been doing lately is context switching between two different tasks, which is not ideal and you do forget what's going on between the two. The alternative seems to be to just be idle. I'm trying to prepare myself for a future where agents are much more autonomous, and I can give them tasks and just have them go run with them. This seems like the path to that, but if anyone has better ideas, I'm all for hearing them.
  • AliceH0521 7 hours ago
    [dead]