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

Parallel AI agents are a game changer

morningcoffee.io

Post reply on HN
Print view View original

41–50 of 88 posts

Re: Parallel AI agents are a game changer

#41

Post by mmaunder »

The author is lying. My team and I are heavy users of Claude code and other agents and it ain’t like this. You need to manage an AI coding agent carefully and course correct frequently. There are cases for parallel agents but they are tasks like parallel document fetches and summarization, and other tasks that don’t require supervision.

The idea of having multiple parallel agents merge pull requests or resolve issues in parallel is still just an idea.

Please don’t post or upvote attention seeking crap like this. It gives a very exciting and promising technology a bad name.

Re: Parallel AI agents are a game changer

#42

Post by pvtmert »

Is it me or the post sounding (showing!) that they haven't tried the mentioned approach in real life.

Because in real life, one agent tries to fix build issue with rm -rf node_modules and the other is already running a server (ie: npm server), conflicting with each other nearly all the time!. (even if it's not a destructive action, the second npm server will most likely to fail due to port-allocation conflicts!)

Meanwhile, what I found helpful is that: 1. Clone the same repo twice or three times 2. In each terminal or whatever, `cd` into it 3. Create a branch, run your ~commands~ prompts (each is their own session with their own repo) 4. commit/push then merge/rebase (also resolve conflicts if needed, use LLM again if you want)

Any other way multiple agents work in harmony in a single repo (filesystem/directory) at the same time is a pipe-dream with the current status of the MCP and agents.

Let alone being aware of each other (agents), they don't even have a proper locking mechanism. As soon as you make a new change, most of the editing (search/replace) functionality in the MCPs fail miserably. Then they re-read the entire file, just creating context-rot or over-filling with already-existing stuff. Soon you run out of tokens (or just pay extra for no reason)

> edit: comments mentioned that each agent runs in a VM isolated from others, kinda makes sense but still, there will be massive merge-conflicts unless each agent runs in a completely different set of service/code-base (ie frontend vs backend or couple of micro-services)

Re: Parallel AI agents are a game changer

#43

Post by lazide »

Aeolun wrote: post #26
DetroitThrow wrote: post #19

Earlier quoted context omitted.

>This is just software engineering?!? Absolutely. The existence of vibe coding does not mean production code is going to be engineered without the same principles we've always used - even if we're using AI to generate a lot more code than before. Any crowd suggesting that this was not the case has lost the plot, imo.

People find it a lot more palatable when the AI requires all this information than when software engineers do though. If I ask for clear requirements I’m asked to just figure it out. But if the AI implements nonsense without clear requirements that the fault of the specs.

Well, that’s because the software engineers are irritating when they push back and say ‘no’ or ‘wtf’.

When the AI does it, it’s being polite and stuff. /s, kinda.

Re: Parallel AI agents are a game changer

#45

Post by adriand »

osn9363739 wrote: post #38
_345 wrote: post #24

Earlier quoted context omitted.

Are you saying that because you're also skeptical? I haven't had the best time switching to agent coding. I mean for throwaway work its fine but its kind of boring and aider still messes up from time to time

I probably lean on the sceptical side of the spectrum. I'm not against giving it a go if I can get value out of it but I'm not having the wonderful experience that these people are having. - The asynchronous nature of it slows me down and it feels the opposite of what this bloke is saying around getting into a flow. - I miss things because I'm not thinking it all the way through. - The issues with errors or hallucina…

Try as an initial step having the agentic AI improve your prompt for you. I have a "prompt improvement prompt template", which is a standardized document (customized for each project I'm working on), that has a bunch of boilerplate instructions in it, along with a section where I paste in my first-draft prompt. I then feed this document (boilerplate + crappy prompt) into the AI and it creates a way better prompt for me. Then I edit that to ensure it's correct, and then that becomes the prompt I use.

Re: Parallel AI agents are a game changer

#46

Post by tjr »

Aeolun wrote: post #26
DetroitThrow wrote: post #19

Earlier quoted context omitted.

>This is just software engineering?!? Absolutely. The existence of vibe coding does not mean production code is going to be engineered without the same principles we've always used - even if we're using AI to generate a lot more code than before. Any crowd suggesting that this was not the case has lost the plot, imo.

People find it a lot more palatable when the AI requires all this information than when software engineers do though. If I ask for clear requirements I’m asked to just figure it out. But if the AI implements nonsense without clear requirements that the fault of the specs.

I am amazed at how suddenly people are on board with writing clear design documentation now that it means AI can generate the code rather than humans.

I wonder how much better humans would be at generating code given the same abundance of clearly-written design documentation?

Re: Parallel AI agents are a game changer

#47

Post by lazide »

shiroyasha wrote: post #29
asdev wrote: post #23

Context switching between more than 2 threads of work is untenable if you want to really review code in depth. And with AI, you need to go through everything with a fine toothed comb

The same work as any senior software engineer reviewing his teams work, imho.

Eh, you quickly learn who you can trust and who needs the super skeptical detailed look with humans. With LLM’s you have you to super skeptical of everything.

Re: Parallel AI agents are a game changer

#48

Post by GZGavinZhao »

pvtmert wrote: post #42

Is it me or the post sounding ( showing! ) that they haven't tried the mentioned approach in real life. Because in real life, one agent tries to fix build issue with rm -rf node_modules and the other is already running a server (ie: npm server), conflicting with each other nearly all the time! . (even if it's not a destructive action, the second npm server will most likely to fail due to port-allocation conflicts!) M…

git workspaces?

Re: Parallel AI agents are a game changer

#49

Post by CuriouslyC »

tptacek wrote: post #35

So: (1) I feel like most people call these async agents, though maybe "parallel" is the term that will stick. (2) Async is great for reasons other than concurrent execution. (3) Concurrent execution is tricky, at least for tightly defined projects, because the PRs will step on each other, and (maybe this is just me) I would rather rewrite an entire project than try to pick through a complicated merge conflict.

Nah, I saw this problem a while ago and already spec'd out the solution. First, agents need to be doing atomic commits, and second you can just have a massive merge queue with bisection, if you're using bazel you can handle ci gating on thousands of PRs with very little overhead, and when a merge batch fails you find the bad patch set in O(log(n)) time and dispatch to an agent for reconciliation. I even built a prototype, works great in benchmarks but I don't have a need for it over merge trains in gitlab yet.

Re: Parallel AI agents are a game changer

#50

Post by hu3 »

mmaunder wrote: post #41

The author is lying. My team and I are heavy users of Claude code and other agents and it ain’t like this. You need to manage an AI coding agent carefully and course correct frequently. There are cases for parallel agents but they are tasks like parallel document fetches and summarization, and other tasks that don’t require supervision. The idea of having multiple parallel agents merge pull requests or resolve issues…

Your comment is disproportionately rude. Just because your team can't leverage multiple coding agents doesn't mean no one else can.

And even if OP also can't, this is a good place to discuss possible problems and solutions for parallel development using coding agents.

Please refrain from gatekeeping.

Post reply on HN