| ▲ | kamranjon a day 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 a day ago | parent | next [-] |
| 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 a day ago | parent | prev | next [-] |
| 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 a day ago | parent | next [-] | | >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) | | |
| ▲ | SyneRyder a day ago | parent [-] | | This is my experience as well. Lots of success with running one hour Fable sessions (one hour of API time). Not using a loop here, but there's often lots of documentation for Claude to go through first before building out the project. The main failure point for me with long running Fable sessions now is just that it might hit a safety guardrail and downgrade to Opus midway. |
| |
| ▲ | adam_arthur a day ago | parent | prev [-] | | 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 a day ago | parent | prev | next [-] |
| 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. |
| |
| ▲ | throwaway7783 a day ago | parent | next [-] | | What do these workflows do? I can't think of anything that needs to run for so long. | | |
| ▲ | kasey_junk a day ago | parent [-] | | Pretty straight ahead coding workflows. Most of my operational workflows are much simpler (because diagnosing an operational issue is much more time sensitive obviously). | | |
| ▲ | ryandrake a day ago | parent [-] | | As a casual AI code user, I can’t even go 30 seconds without claude grinding to a halt asking for permission to run a bash script for the 10th time. | | |
| ▲ | kasey_junk a day ago | parent [-] | | The first step is building a sandbox (vm, container, whatever) that allows you to trust the agent in its most permissive mode. This varies based on the maturity of my projects but most of my sessions live in VMs with very specific egress rules and permissions. | | |
| ▲ | londons_explore a day ago | parent | next [-] | | Frustratingly none of the coding harnesses seem to default to just firing up a docker container with the working directory mounted and letting the AI run wild inside the container. | | |
| ▲ | kasey_junk a day ago | parent [-] | | You can get that working for yourself trivially. My agent environment now has 3 different kinds of compute abstractions, 3 different agents and a nascent workflow engine in it. It works how _i_ want, which is really refreshing. | | |
| ▲ | londons_explore 21 hours ago | parent [-] | | Oh I've built the same too. But it took me a few hours to work out the quirks, when it should just be the default. |
|
| |
| ▲ | ryandrake a day ago | parent | prev [-] | | I think this is an area where the developers of the agent harnesses should be spending a lot of effort. It's not reasonable to expect your users to set up and maintain a VM just to safely use a tool. When I run cmake, I don't have to worry about it accidentally deleting my root filesystem or posting my account credentials to github. Most of the command line coding tools I use don't even need/have a --dry-run option. | | |
| ▲ | kasey_junk a day ago | parent [-] | | Could be. But a) I don’t know why I’d trust them to do that when existing tooling means I don’t have to and b) this is not a new paradigm for me. I’ve been running most of my dev environments in sandboxed mode for a long time. I don’t trust npm either. |
|
|
|
|
| |
| ▲ | eru a day ago | parent | prev | next [-] | | I assume a lot of these 8-10 hours are spend calling tools and getting feedback from that? | | | |
| ▲ | throw1234567891 a day ago | parent | prev [-] | | I have the same on local models. |
|
|
| ▲ | jdthedisciple a day ago | parent | prev | next [-] |
| I recently had GPT 5.6 work on something for 54 minutes while I went to sleep |
| |
| ▲ | MRiabov a day ago | parent [-] | | 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 a day ago | parent | prev | next [-] |
| K3 is relatively slow, but 12 minutes points to the harness not the model IMO. |
|
| ▲ | _zoltan_ a day ago | parent | prev | next [-] |
| I have Claude workflows that it takes 30+ minutes to get any feedback while it thinks |
|
| ▲ | brcmthrowaway a day ago | parent | prev [-] |
| What local model? |
| |
