Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agents that run while I sleep

claudecodecamp.com

Post reply on HN
Print view View original

51–60 of 532 posts

Re: Agents that run while I sleep

#51

Post by kwanbix »

afro88 wrote: post #30

I guess to reach this point you have already decided you don't care what the code looks like. Something I'm starting to struggle with is when agents can now do longer and more complex tasks, how do you review all the code? Last week I did about 4 weeks of work over 2 days first with long running agents working against plans and checklists, then smaller task clean ups, bugfixes and refactors. But all this code needs t…

So you have become a reviewer instead of a programmer? Is that so? hones question. And if so, what is the advantage of looking a code for 12 hours instead of coding for 12.

Re: Agents that run while I sleep

#52

Post by irishcoffee »

dmd wrote: post #43
codybontecou wrote: post #34

Earlier quoted context omitted.

This sounds interesting. Can you go a bit deeper or provide references on how to implement the green/red/refactor subagent pattern?

That's the cool bit - you don't have to. CC is perfectly well aware and competent to implement it; just tell it to.

"So this is how liberty dies... with thunderous applause.” - Padmé Amidala

s/liberty/knowledge

Re: Agents that run while I sleep

#53

Post by zer00eyz »

afro88 wrote: post #30

I guess to reach this point you have already decided you don't care what the code looks like. Something I'm starting to struggle with is when agents can now do longer and more complex tasks, how do you review all the code? Last week I did about 4 weeks of work over 2 days first with long running agents working against plans and checklists, then smaller task clean ups, bugfixes and refactors. But all this code needs t…

> how do you review all the code?

Code review is a skill, as is reading code. You're going to quickly learn to master it.

> It's like 20k of line changes over 30-40 commits.

You run it, in a debugger and step through every single line along your "happy paths". You're building a mental model of execution while you watch it work.

> One solution is to start from scratch again, using this branch as a reference, to reimplement in smaller PRs. I'm not sure this would actually save time overall though.

Not going to be a time saver, but next time you want to take nibbles and bites, and then merge the branches in (with the history). The hard lesson here is around task decomposition, in line documentation (cross referenced) and digestible chunks.

But if you get step debugging running and do the hard thing of getting through reading the code you will come out the other end of the (painful) process stronger and better resourced for the future.

Re: Agents that run while I sleep

#54

Post by mgrassotti »

tavavex wrote: post #37
comradesmith wrote: post #12

Earlier quoted context omitted.

1. Make tests 2. Commit them 3. Proceed with implementation and tell agent to use the tests but not modify them It will probably comply, and at least if it does change the tests you can always revert those files to where you committed them

Are there really no ways to control read/write permissions in a smart way? I've not had to do this yet, but is it really only capable of either being advisory with you implementing all the code, or it having full control over the repo where you just hope nothing important is changed? You could probably make a system-level restriction so the software physically can't modify certain files, but I'm not sure how well tha…

You can use a Claude PreToolUse command hook to prevent write (or even read) access to specific files.

With this approach you can enforce that Claude cannot access to specific files. It’s a guarantee and will always work, unlike a prompt or Claude.md which is just a suggestion that can be forgotten or ignored.

This post has an example hook for blocking access to sensitive files:

https://aiorg.dev/blog/claude-code-hooks#:~:text=Protect%20s...

Re: Agents that run while I sleep

#55

Post by vitro »

BeetleB wrote: post #38
comradesmith wrote: post #12

Earlier quoted context omitted.

1. Make tests 2. Commit them 3. Proceed with implementation and tell agent to use the tests but not modify them It will probably comply, and at least if it does change the tests you can always revert those files to where you committed them

No. I don't want the mental burden of auditing whether it modified the tests.

Then, run the agent vm-sandboxed, with tests mounted as a read-only directory, if your directory structure allows it.

Re: Agents that run while I sleep

#57

Post by afro88 »

egeozcan wrote: post #26

You can always tell claude to use red-green-refactor and that really is a step-up from "yeah don't forget to write tests and make sure they pass" at the end of the prompt, sure. But even better, tell it to create subagents to form red team, green team and refactor team while the main instance coordinates them, respecting the clean-room rules. It really works. The trick is just not mixing/sharing the context. Differen…

Good idea, and an improvement, but you still have that fundamental issue: you don't really know what code has been written. You don't know the refactors are right, in alignment with existing patterns etc.

Re: Agents that run while I sleep

#58

Post by jakewins »

bhouston wrote: post #32

I call this "Test Theatre" and it is real. I wrote about it last year: https://benhouston3d.com/blog/the-rise-of-test-theater You have to actively work against it.

This was really good, and second leaning on property testing. I’ve had really good outcomes from setting up Schemathesis and getting blanket coverage for stuff like “there should be no request you can generate as logged in user A that let’s you do things as or see things that belong to user B”, as well as “there should be no request you can find to any API endpoint that can trigger a 5xx response”

Re: Agents that run while I sleep

#59

Post by darkbatman »

aray07 wrote: post #29
egeozcan wrote: post #26

You can always tell claude to use red-green-refactor and that really is a step-up from "yeah don't forget to write tests and make sure they pass" at the end of the prompt, sure. But even better, tell it to create subagents to form red team, green team and refactor team while the main instance coordinates them, respecting the clean-room rules. It really works. The trick is just not mixing/sharing the context. Differen…

thats a great idea - i have been using codex to do my code reviews since i have it to give better critique on code written by claude but havent tried it with testing yet!

codex/gpt is a stubborn model, doubt it would accept claude reviews or counter it. have seen cases where claude is more willing to comply if shared feedback though its just sycophancy too.

Re: Agents that run while I sleep

#60

Post by lagrange77 »

magicalist wrote: post #47
egeozcan wrote: post #26

You can always tell claude to use red-green-refactor and that really is a step-up from "yeah don't forget to write tests and make sure they pass" at the end of the prompt, sure. But even better, tell it to create subagents to form red team, green team and refactor team while the main instance coordinates them, respecting the clean-room rules. It really works. The trick is just not mixing/sharing the context. Differen…

> But even better, tell it to create subagents to form red team, green team and refactor team while the main instance coordinates them, respecting the clean-room rules. It really works. It helps, but it definitely doesn't always work, particularly as refactors go on and tests have to change. Useless tests start grow in count and important new things aren't tested or aren't tested well. I've had both Opus 4.6 and Code…

> Reward hacking is very real and hard to guard against.

Is it really about rewards? Im genuinely curious. Because its not a RL model.

Post reply on HN