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

21–30 of 147 posts

Re: Embracing the parallel coding agent lifestyle

#21

Post by joshvm »

grim_io wrote: post #13

I'm not convinced there is any hope for a productive, long-term, burnout-free parallel agent workflow. Not while they need even the slightest amount of supervision/review.

My suspicion is that it's because the feedback loop is so fast. Imagine if you were tasked with supervising 2 co-workers who gave you 50-100 line diffs to review every minute. The uncanny valley is that the code is rarely good enough to accept blindly, but the response is quick enough that it feels like progress. And perhaps an human impulse to respond to the agent? And a 10-person team? In reality those 10 people would review each other's PRs and in a good organisation you trust each other to gatekeep what gets checked in. The answer sounds like managing-agents, but none of the models are good enough to reliably say what's slop and what's not.

Re: Embracing the parallel coding agent lifestyle

#22

Post by grim_io »

joshvm wrote: post #21
grim_io wrote: post #13

I'm not convinced there is any hope for a productive, long-term, burnout-free parallel agent workflow. Not while they need even the slightest amount of supervision/review.

My suspicion is that it's because the feedback loop is so fast. Imagine if you were tasked with supervising 2 co-workers who gave you 50-100 line diffs to review every minute. The uncanny valley is that the code is rarely good enough to accept blindly, but the response is quick enough that it feels like progress. And perhaps an human impulse to respond to the agent? And a 10-person team? In reality those 10 people wo…

I don't like to compare LLM's to people.

There is a real return of investment in co-workers over time, as they get better (most of the time).

Now, I don't mind engaging in a bit of Sisyphean endeavor using an LLM, but remember that the gods were kind enough to give him just one boulder, not 10 juggling balls.

Re: Embracing the parallel coding agent lifestyle

#23

Post by Multiplayer »

aantix wrote: post #14

Along these lines, how does everyone visually organize the multiple terminal tabs open for these numerous agents in various states? I wish there were a way to search across all open tabs. I've started color-coding my Claude code tabs, all red, which helps me to find them visually. I do this with a preexec in my ~/.zshrc. But wondering if anyone else has any better tricks for organizing all of these agent tabs? I'm us…

This may not be your cup of tea but I'm using stage manager on Mac for the first time after hating on it for years, for exactly this. I've got 3 monitors and they all have 4-6 stage manager windows. I bundle the terminals, web browser and whatever into these windows. Easily switching from project to project.

Re: Embracing the parallel coding agent lifestyle

#24

Post by ragnese »

joshvm wrote: post #21
grim_io wrote: post #13

I'm not convinced there is any hope for a productive, long-term, burnout-free parallel agent workflow. Not while they need even the slightest amount of supervision/review.

My suspicion is that it's because the feedback loop is so fast. Imagine if you were tasked with supervising 2 co-workers who gave you 50-100 line diffs to review every minute. The uncanny valley is that the code is rarely good enough to accept blindly, but the response is quick enough that it feels like progress. And perhaps an human impulse to respond to the agent? And a 10-person team? In reality those 10 people wo…

Yes. The first time I heard/read someone describe this idea of managing parallel agents, my very first thought was that this is only even a thing because the LLM coding tools are still slow enough that you can't really achieve a good flow state with the current state of the art. On the flip side of that, this kind of workflow is only sustainable if the agents stay somewhat slow. Otherwise, if the agents are blocking on your attention, it seems like it would feel very hectic and I could see myself getting burned out pretty quickly from having to spend my whole work time doing a round-robin on iterating each agent forward.

I say that having not tried this work flow at all, so what do I know? I mostly only use Claude Code to bounce questions off of and ask it to do reviews of my work, because I still haven't had that much luck getting it to actually write code that is complete and how I like.

Re: Embracing the parallel coding agent lifestyle

#25

Post by dirck-norman »

I’ve seen minimal gains trying to adopt agents into my workflow beyond tests and explanations. It tends to be distracting.

It’s so interesting that engineers will criticize context switching, only to adopt it into their technical workflows because it’s pitched as a technical solution rather than originating from business needs.

Re: Embracing the parallel coding agent lifestyle

#27

Post by laterium »

xnx wrote: post #11

We are at a weird moment where the latency of the response is slow enough that we're anthropomorphizing AI code assistants into employees. We don't talk about image generation this way. With images, its batching up a few jobs and reviewing the results later. We don't say "I spun up a bunch of AI artists."

As a follow-up, how would this workflow feel if the LLM generation were instantenous or cost nothing? What would the new bottleneck be? Running the tests? Network speed? The human reviewer?

Re: Embracing the parallel coding agent lifestyle

#29

Post by simonw »

grim_io wrote: post #13

I'm not convinced there is any hope for a productive, long-term, burnout-free parallel agent workflow. Not while they need even the slightest amount of supervision/review.

The thing that's working really well for me is parallel research tasks.

I can pay full attention to the change I'm making right now, while having a couple of coding agents churning in the background answering questions like:

"How can I resolve all of the warnings in this test run?"

Or

"Which files do I need to change when working on issue #325?"

I also really like the "Send out a scout" pattern described in https://sketch.dev/blog/seven-prompting-habits - send an agent to implement a complex feature with no intention of actually using their code - but instead aiming to learn from which files and tests they updated, since that forms a useful early map for the actual work.

Re: Embracing the parallel coding agent lifestyle

#30

Post by cuttothechase »

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 with a proven paradigm?

Post reply on HN