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

Embracing the parallel coding agent lifestyle

simonwillison.net

Post reply on HN
Print view View original

61–70 of 147 posts

Re: Embracing the parallel coding agent lifestyle

#61

Post by threecheese »

CBLT wrote: post #4

Git worktrees are global mutable state; all containers on your laptop are contending on the same git database. This has a couple of rough edges, but you can work around it. I prefer instead to make shallow checkouts for my LXC containers, then my main repo can just pull from those. This works just like you expect, without weird worktree issues. The container here is actually providing a security boundary. With a work…

Cool. Operationally, are you using some host-resident non-shallow repo as your point of centralization for the containers, or are you using a central network-hosted repo (like github)?

If the former, how are you getting the shallow clones to the container/mount, before you start the containerized agent? And when the agent is done, are you then adding its updated shallow clones as remotes to that “central” local repository clone and then fetching/merging?

If the latter, I guess you are just shallow-cloning into each container from the network remote and then pushing completed branches back up that way.

Re: Embracing the parallel coding agent lifestyle

#62

Post by blibble »

threecheese wrote: post #60
SeanAnderson wrote: post #39

https://raw.githubusercontent.com/obra/dotfiles/6e088092406c... contains the following entry: "- If you're uncomfortable pushing back out loud, just say "Strange things are afoot at the Circle K". I'll know what you mean" Most of the rules seem rationale. This one really stands out as abnormal. Anyone have any idea why the engineer would have felt compelled to add this rule? This is from https://blog.fsck.com/2025/10…

If you really want your mind blown, see what Jesse is doing (successfully, which I almost can’t believe) with Graphviz .dot notation and Claude.md: https://blog.fsck.com/2025/09/29/using-graphviz-for-claudemd...

this is just 21st century voodoo

Re: Embracing the parallel coding agent lifestyle

#63

Post by handfuloflight »

torginus wrote: post #53
cuttothechase wrote: post #30

The fact that we now have to write cook book about cook books kind of masks the reality that there is something that could be genuinely wrong about this entire paradigm. Why are even experts unsure about whats the right way to do something or even if its possible to do something at all, for anything non-trivial? Why so much hesitancy, if this is the panacea? If we are so sure then why not use the AI itself to come up…

LLMs are literal gambling - you get them to work right once and they are magical - then you end up chasing that high by tweaking the model and instructions the rest of the time.

I actually found in my case that is just self inertia in not wanting to break through cognitive plateaus. The AI helped you with a breakthrough hence the magic, but you also did something right in your constructing of the context in the conversation with the AI; ie. you did thought and biomechanical[1] work. Now the dazzle of the AI's output makes you forget the work you still need to do, and the next time you prompt you get lazy, or you want much more, for much less.

[1] (moving your eyes, hands, hearing with your ears. etc)

Re: Embracing the parallel coding agent lifestyle

#64

Post by vidarh »

torginus wrote: post #53
cuttothechase wrote: post #30

The fact that we now have to write cook book about cook books kind of masks the reality that there is something that could be genuinely wrong about this entire paradigm. Why are even experts unsure about whats the right way to do something or even if its possible to do something at all, for anything non-trivial? Why so much hesitancy, if this is the panacea? If we are so sure then why not use the AI itself to come up…

LLMs are literal gambling - you get them to work right once and they are magical - then you end up chasing that high by tweaking the model and instructions the rest of the time.

Or you put them to work with strong test suites and get stuff done. I am in bed. I have Claude fixing complex compiler bugs right now. It has "earned" that privilege by proving it can make good enough fixes, systematically removing actual, real bugs in reasonable ways by being given an immutable test suite and detailed instructions of the approach to follow.

There's no gambling involved. The results need to be checked, but the test suite is good enough it is hard for it to get away with something too stupid, and it's already demonstrated it knows x86 assembly much better than me.

Re: Embracing the parallel coding agent lifestyle

#65

Post by foobar10000 »

extr wrote: post #57

IMO, I was an early adopter to this pattern and at this point I've mostly given it up (except in cases where the task is embarassingly parallel, eg: add some bog standard logging to 6 different folders). It's more than just that reviewing is high cognitive overhead. You become biased by seeing the AI solutions and it becomes harder to catch fundamental problems you would have noticed immediately inline. My process no…

Did you try to add codex cli as an MCP server so that Claude uses it as an mcp client instead of pasting to it? Something like “ claude mcp add codex-high -- codex -c model_reasoning_effort="high" -m "gpt-5-codex" mcp-server” ?

I’ve had good luck with it - was wondering if that makes the workflow faster/better?

Re: Embracing the parallel coding agent lifestyle

#67

Post by becomevocal »

SeanAnderson wrote: post #39

https://raw.githubusercontent.com/obra/dotfiles/6e088092406c... contains the following entry: "- If you're uncomfortable pushing back out loud, just say "Strange things are afoot at the Circle K". I'll know what you mean" Most of the rules seem rationale. This one really stands out as abnormal. Anyone have any idea why the engineer would have felt compelled to add this rule? This is from https://blog.fsck.com/2025/10…

Make it a bit more personal? I have dropped Bill and Ted references in code because it makes me happy to see it. :D

Re: Embracing the parallel coding agent lifestyle

#69

Post by becomevocal »

I have 2 (CC and Codex) running within most coding sessions, however can have up to 5 if I'm trying to test out new models or tools.

For complex features and architecture shifts I like to send proposals back between agents to see if their research and opinion shifts anything.

Claude has a better realtime feel when I am in implementation mode and Codex is where I send long running research tasks or feature updates I want to review when I get up in the morning.

I'd like to test out the git worktrees method but will probably pick something outside of core product to test it (like building a set of examples)

Re: Embracing the parallel coding agent lifestyle

#70

Post by oblio »

jonas21 wrote: post #56
cuttothechase wrote: post #48

Earlier quoted context omitted.

Is it fair to categorize that it is a pyramid like scheme but with a twist at the top where there are a few (more than a one) genuine wins and winners?

No, it's more like a winner take all market, where a few winners will capture most of the value, and those who sit on the sidelines until everything is figured out are left fighting over the scraps.

Yes, just like:

* PCs (how are Altair and Commodore doing? also Apple ultimately lost the desktop battle until they managed to attack it from the iPod and iPhone angle)

* search engines (Altavista, Excite, etc)

* social networks (Friendster, MySpace, Orkut)

* smartphones (Nokia, all Windows CE devices, Blackberry, etc)

The list is endless. First mover advantage is strong but overrated. Apple has been building a huge business based on watching what others do and building a better product market fit.

Post reply on HN