← Back to context

Comment by thevinter

2 days ago

Personal anecdote: I exhausted my Claude usage yesterday so I decided to spend 20$ to try Kimi while I was at it. Logged in, paid, downloaded Kimi Code, set it to use K3 and prompted something along the lines of: "Check this repository and find all the settings that can be passed as input related to hardware, I/O, thread control or networking. Produce a report".

It thought for about 12 minutes and then told me I had exhausted my daily quota. (The next day Fable did the same task in 3m)

If you want to buy a plan for K3 do NOT buy the 20$ one.

37 comments

thevinter

Reply
kamranjon  2 days ago

So I am likely coming from a completely different world because I use entirely self hosted models - but is it really common in your workflows to just wait for 12 minutes without any feedback? I am constantly watching my model and following the path it’s taking and cutting it off or steering it if it’s headed down a dead path. I was just curious if this is really common to just have no feedback for 12 minutes?

  • thevinter  2 days ago

    Well, to be clear, there was some feedback (e.g. it was calling subagents and printing some thinking messages).

    That said, yes, it is pretty common for me to wait 10, 20 and sometimes even 30 minutes without steering the model or looking at what its doing. I usually write a pretty detailed prompt at the start that describes the issue, the usecases, the testing to do and the definition of success; then I sometimes ask it to draft a plan and give it a read, but after that I just press enter, let it run and come back when it's done.

    In the end I do a manual review, both of the code and the functionality, but most of the time I get exactly what I wanted.

  • roncesvalles  2 days ago

    Usually, the longer the AI works on something the crappier its output because that means the context is getting filled up.

    If my AI prompt takes more than 5 minutes to execute, I'm almost certain to stop it and break up the task or be more specific about what files it should look at or what subtask it should tackle first. The people who let it run for hours are absolutely not getting anything worth keeping in the end.

    • AussieWog93  2 days ago

      >Usually, the longer the AI works on something the crappier its output because that means the context is getting filled up.

      This was definitely truer with older models but isn't necessarily the case now.

      They frequently do other things apart from navel-gazing that take a lot of time but get good results, like spinning up subagents to solve some hairy task in a loop.

      Stopping/distrusting long-running AIs is a habit I've had to unlearn myself.

      I frequently get good results from a 30+ minute Fable session, when I've asked it to do something complex (e.g. run the QA tester in a loop and eliminate all crashes, one commit per crash fixed)

      1 reply →

    • adam_arthur  2 days ago

      Exactly.

      I've found 6 minutes or so the sweet spot for upper bound with 5.6 Sol.

      And it sounds like the OPs query above requires scanning throughout a large portion of the codebase, which will inherently consume a large number of input tokens. No locality to it.

  • kasey_junk  2 days ago

    I have workflows that run for 8-10 hours unattended regularly. This is on frontier models though.

    But if I were to look in on them they’d be giving feedback during that time, but they wouldn’t need steering.

  • jdthedisciple  2 days ago

    I recently had GPT 5.6 work on something for 54 minutes while I went to sleep

    • MRiabov  2 days ago

      I had two agents work from 7pm to 6am today... a routine for me.

      Today we needed to migrate to a cheaper CI/CD provider and do a better robotic for a particular task. GPT-5.6 Sol.

  • danwitt  2 days ago

    K3 is relatively slow, but 12 minutes points to the harness not the model IMO.

  • _zoltan_  2 days ago

    I have Claude workflows that it takes 30+ minutes to get any feedback while it thinks

satvikpendem  2 days ago

Codex works for this, it'll continue thinking and will answer the prompt even if your limit is reached.

  • wingworks  2 days ago

    I feel like this is the right way to do it. Especially if you're using your own credits. Unless it's obnoxiously long task.

    So often it'll cut off just as it's about to finish.

Altern4tiveAcc  2 days ago

I had the _exact_ same problem. Got the 20 USD/month subscription from Kimi.com (paid annually), exhausted my 5-hour quota with a simple prompt on OpenCode + Kimi K2.7 through their API. Cursor got the same prompt done in minutes.

According to their web interface, I'm also on 23% of my weekly usage. That feels crazy, as I do a lot more than that on the 20 USD Cursor plan, and never got even a warning.

I thought OpenCode was doing something wrong, but you had the same issue with Kimi Code.

  • ffsm8  2 days ago

    Moonshot AI has two subscriptions archetypes and the one they link to from their main page is the subscription for the web interface/research/agents/OpenClaw (that they host for you)

    There is a small link below the tiles for these plans saying something "looking to use it for code? Use Kimi code" and upon clicking you'll get a basically identically looking subscription page with different sub prices and more quota

    Non coding plans:

       * Plus (19 "base agent" -- wahtever that might be)
   * Pro (39 x2 )
   * Max (99 x6)
   * Ultra (199 x12)

    > https://www.kimi.com/membership/pricing

    Coding plans:

        * Starter (19 - "base coding")
    * Explorer (49 - x4)
    * Expert (99 x10)
    * Master (219 x25)

    > https://www.kimi.com/code

    I stumbled on that when i tried Kimi K2.5 back when that was released.

    It's also worth mentioning that the $20 get you a 0.25 priority for API usage - because the others get x4 priority. So get ready for a _slow_ experience

    • Altern4tiveAcc  2 days ago

      Thank you so much. I was about to ask you for links, since they have multiple domains that look similar (kimi.ai, kimi.com, moonshot.ai, etc.). I wasn't sure which one was the legit one, or if they all are.

      The plan I got is called "Moderato", which somehow isn't any of those 8... I'll try to read more about it.

    • sbochins  2 days ago

      That doesn’t appear to be the case anymore. They just have one set of plans: Allegreto, modereto, etc which apply to both the chat app and the coding apps.

      1 reply →

phyzix5761  2 days ago

I had the same experience with Claude the other day. I asked it for something fairly simple and it used up my whole 5 hour quota without producing the answer. Felt like a total waste of time.

throw1234567891  2 days ago

What's the app? nodejs todo app with a "database back end" in a text file, or a 1m line spaghetti code COBOL app from 1971?

zeratax  1 day ago

kinda surprising to me after the macos web demo was apparently done on the $40 monthly coding plan which was like a 6 hour task