Hacker News Reader

Comment by mabunday | Hacker News Reader

I'm not surprised. I used Claude Code for the first time again since April because I had been hearing good things about Opus 5.5 and Fable 5.1, but I was shocked by how bad the harness is and how its only gotten worse since spring? I may be doing something wrong, but getting Opus/Fable to properly spin up non-blocking sub-agents takes like four or five attempts and it still cannot reliably poll tasks like test suites that take more than 30 seconds for proper completion.

I think even if you have the world's best model (not my opinion, but seems to be the popular consensus these days with Anthropic), if the harness around it sucks none of that intelligence is going to matter.

View on HN

You are definitely doing something wrong. All of my sessions constantly use subagents and are able to poll with background tasks.

You are doing something wrong.

I am routinely using swarms of agents, with complex sequencing between them and agents watching other agents, and then triggering forks and/or new design cycles. My normal flow is to have a few design tasks open per codebase during the day, with each design agent aware of the other sessions, and having an unattended nightly build which sometimes takes 8hrs and also requires coordination for tests, merges, and so on.

Did you try once on a bad day?

I experienced a regression some days ago, where Claude Code with Opus 5.5 wouldn't progress as expected, getting stuck on steps. So I had to repeatedly ask it what the status was and to proceed with X, and so on.

But that was just one day, the days before and after it has done lots of fairly autonomous work, including spinning off multiple subagents to run conformance tests which take 30-50 mins and work on other stuff in the meantime, then acting on the results autonomously.

I super agree about the harness opinion, but cc in itself is not a bad one, I'd recommend running the suites as a single blocking command with a long timeout and read the exit code, instead of backgrounding it and polling output.

Not fanboying or playing favorite, but I've never come across what you mentioned while using Claude Code. You may indeed be doing something wrong or some part of your config isn't right.

I use Copilot CLI at work, and Claude Code at home, and all harnesses are pretty good these days.

Hey, Boris from the team here. This is pretty surprising, given background subagents are the default. Could you confirm you’re running the latest, and run /bug and paste the id here? Happy to debug what’s happening

Seriously hope you get that trace because as much as I like to dunk on Claude Code as a harness, it’s definitely not as bad as OP stated, ha.

First off you need to pick a harness that you can use with every model. This way you isolate model problems from harness problems. If you had to switch harnesses (Claude Code) in order to try out Fable, you're doing something wrong.

Secondly yeah, all models have issues with foreground vs background subagents. So I just modified my harness to delete foreground subagents. No more confusion. If they need the subagent's output tokens they can read it from the session transcript.

"Take away tools" is often the best solution for model-gets-confused problems. Narrow down your toolset until there's only one way to do things, and then make it the maximally-powerful way.

Reply on news.ycombinator.com