343 points by AffableSpatula 14 hours ago | 37 comments
hereme888 0 minutes ago
So apparently all swarm features are controlled by a single gate function in Claude Code:

// Default (disabled) function i8() { if (Yz(process.env.CLAUDE_CODE_AGENT_SWARMS)) return !1; return xK("tengu_brass_pebble", !1); }

So, // After patch function i8(){return!0}

mafriese 7 hours ago
Ok it might sound crazy but I actually got the best quality of code (completely ignoring that the cost is likely 10x more) by having a full “project team” using opencode with multiple sub agents which are all managed by a single Opus instance. I gave them the task to port a legacy Java server to C# .NET 10. 9 agents, 7-stage Kanban with isolated Git Worktrees.

Manager (Claude Opus 4.5): Global event loop that wakes up specific agents based on folder (Kanban) state.

Product Owner (Claude Opus 4.5): Strategy. Cuts scope creep

Scrum Master (Opus 4.5): Prioritizes backlog and assigns tickets to technical agents.

Architect (Sonnet 4.5): Design only. Writes specs/interfaces, never implementation.

Archaeologist (Grok-Free): Lazy-loaded. Only reads legacy Java decompilation when Architect hits a doc gap.

CAB (Opus 4.5): The Bouncer. Rejects features at Design phase (Gate 1) and Code phase (Gate 2).

Dev Pair (Sonnet 4.5 + Haiku 4.5): AD-TDD loop. Junior (Haiku) writes failing NUnit tests; Senior (Sonnet) fixes them.

Librarian (Gemini 2.5): Maintains "As-Built" docs and triggers sprint retrospectives.

You might ask yourself the question “isn’t this extremely unnecessary?” and the answer is most likely _yes_. But I never had this much fun watching AI agents at work (especially when CAB rejects implementations). This was an early version of the process that the AI agents are following (I didn’t update it since it was only for me anyway): https://imgur.com/a/rdEBU5I

alphazard 2 hours ago
Every time I read something like this, it strikes me as an attempt to convince people that various people-management memes are still going to be relevant moving forward. Or even that they currently work when used on humans today. The reality is these roles don't even work in human organizations today. Classic "job_description == bottom_of_funnel_competency" fallacy.

If they make the LLMs more productive, it is probably explained by a less complicated phenomenon that has nothing to do with the names of the roles, or their descriptions. Adversarial techniques work well for ensuring quality, parallelism is obviously useful, important decisions should be made by stronger models, and using the weakest model for the job helps keep costs down.

rlayton2 2 hours ago
My understanding is that the main reason splitting up work is effective is context management.

For instance, if an agent only has to be concerned with one task, its context can be massively reduced. Further, the next agent can just be told the outcome, it also has reduced context load, because it doesn't need to do the inner workings, just know what the result is.

For instance, a security testing agent just needs to review code against a set of security rules, and then list the problems. The next agent then just gets a list of problems to fix, without needing a full history of working it out.

purplepatrick 1 hour ago
I’ve found that task isolation, rather than preserving your current session’s context budget, is where subagents shine.

In other words, when I have a task that specifically should not have project context, then subagents are great. Claude will also summon these “swarms” for the same reason. For example, you can ask it to analyze a specific issue from multiple relevant POVs, and it will create multiple specialized agents.

However, without fail, I’ve found that creating a subagent for a task that requires project context will result in worse outcomes than using “main CC”, because the sub simply doesn’t receive enough context.

fphhotchips 2 hours ago
Which, ultimately, is not such a big difference to the reason we split up work for humans, either. Human job specialization is just context management over the course of 30 years.
simondotau 47 minutes ago
I suppose it’s could end up being an LLM variant of Conway’s Law.

“Organizations are constrained to produce designs which are copies of the communication structures of these organizations.”

https://en.wikipedia.org/wiki/Conway%27s_law

ttoinou 1 hour ago
Developers do want managers actually, to simplify their daily lives. Otherwise they would self manage themselves better and keep more of the share of revenues for them
shermantanktop 42 minutes ago
Unfortunately some managers get lonely and want a friendly face in their org meetings, or can’t answer any technical questions, or aren’t actually tracking what their team is doing. And so they pull in an engineer from their team.

Being a manager is a hard job but the failure mode usually means an engineer is now doing something extra.

AlexErrant 2 hours ago
For those ignorant, CAB is Change-advisory board

https://en.wikipedia.org/wiki/Change-advisory_board

DanOpcode 2 hours ago
Very cool! A couple of questions:

1. Are you using a Claude Code subscription? Or are you using the Claude API? I'm a bit scared to use the subscription in OpenCode due to Anthropic's ToS change.

2. How did you choose what models to use in the different agents? Do you believe or know they are better for certain tasks?

juanre 5 hours ago
I have been using a simpler version of this pattern, with a coordinator and several more or less specialized agents (eg, backend, frontend, db expert). It really works, but I think that the key is the coordinator. It decreases my cognitive load, and generally manages to keep track of what everyone is doing.
_alex_ 52 minutes ago
Interesting that your impl agents are not opus. I guess having the more rigorous spec pipeline helps scope it to something sonnet can knock out.
kaspermarstal 4 hours ago
Can you share technical details please? How is this implemented? Is it pure prompt-based, plugins, or do you have like script that repeatedly calls the agents? Where does the kanban live?
mogili1 4 hours ago
Not the OP, but this is how I manage my coding agent loops:

I built a drag and drop UI tool that sets up a sequence of agent steps (Claude code or codex) and have created different workflows based on the task. I'll kick them off and monitor.

Here's the tool I built for myself for this: https://github.com/smogili1/circuit

RestartKernel 3 hours ago
What are the costs looking like to run this? I wonder whether you would be able to use this approach within a mixture-of-experts model trained end-to-end in ensemble. That might take out some guesswork insofar the roles go.
tehlike 47 minutes ago
You probably implemented gastown.
taspeotis 3 hours ago
ceroxylon 2 hours ago
What are you building with the code you are generating?
ggoo 7 hours ago
Is this satire?
mafriese 6 hours ago
Nope it isn’t. I did it as a joke initially (I also had a version where every 2 stories there was a meeting and if a someone underperformed it would get fired). I think there are multiple reasons why it actually works so well:

- I built a system where context (+ the current state + goal) is properly structured and coding agents only get the information they actually need and nothing more. You wouldn’t let your product manager develop your backend and I gave the backend dev only do the things it is supposed to and nothing more. If an agent crashes (or quota limits are reached), the agents can continue exactly where the other agents left off.

- Agents are ”fighting against” each other to some extend? The Architect tries to design while the CAB tries to reject.

- Granular control. I wouldn’t call “the manager” _a deterministic state machine that is calling probabilistic functions_ but that’s to some extent what it is? The manager has clearly defined tasks (like “if file is in 01_design —> Call Architect)

Here’s one example of an agent log after a feature has been implemented from one of the older codebases: https://pastebin.com/7ySJL5Rg

ggoo 6 hours ago
Thanks for clarifying - I think some of the wording was throwing me off. What a wild time we are in!
stavros 6 hours ago
What OpenCode primitive did you use to implement this? I'd quite like a "senior" Opus agent that lays out a plan, a "junior" Sonnet that does the work, and a senior Opus reviewer to check that it agrees with the plan.
mafriese 6 hours ago
You can define the tools that agents are allowed to use in the opencode.json (also works for MCP tools I think). Here’s my config: https://pastebin.com/PkaYAfsn

The models can call each other if you reference them using @username.

This is the .md file for the manager : https://pastebin.com/vcf5sVfz

I hope that helped!

stavros 6 hours ago
This is excellent, thank you. I came up with half of this while waiting for this reply, but the extra pointers about mentioning with @ and the {file} syntax really helps, thanks again!
overfeed 5 hours ago
> [...]coding agents only get the information they actually need and nothing more

Extrapolating from this concept led me to a hot-take I haven't had time to blog about: Agentic AI will revive the popularity of microservices. Mostly due to the deleterious effect of context size on agent performance.

throwup238 5 hours ago
Why would they revive the popularity of microservices? They can just as well be used to enforce strict module boundaries within a modular monolith keeping the codebase coherent without splitting off microservices.
simultsop 6 hours ago
quite a storyteller
nobody_r_knows 4 hours ago
I'm confused when you say you have a manager, scrum master, archetech, all supposdely sharing the same memory, do each of those "employees" "know" what they are? And if so, based on what are their identities defined? Prompts? Or something more. Or am I just too dumb to understand / swimming against the current here. Either way, it sounds amazing!
Jimmc414 4 hours ago
Their roles are defined by prompts. Only memory are shared files and the conversation history that’s looped back to stateless API calls to an LLM.
GoatInGrey 6 hours ago
It's not satire but I see where you're coming from.

Applying distributed human team concepts to a porting task squeezes extra performance from LLMs much further up the diminishing returns curve. That matters because porting projects are actually well-suited for autonomous agents: existing code provides context, objective criteria catch more LLM-grade bugs than greenfield work, and established unit tests offer clear targets.

I guess what I'm trying to say is that the setup seems absurd because it is. Though it also carries real utility for this specific use case. Apply the same approach to running a startup or writing a paid service from scratch and you'd get very different results.

vidarh 5 hours ago
I don't know about something this complex, but right this moment I have something similar running in Claude Code in another window, and it is very helpful even with a much simpler setup:

If you have these agents do everything at the "top level" they lose track. The moment you introduce sub-agents, you can have the top level run in a tight loop of "tell agent X to do the next task; tell agent Y to review the work; repeat" or similar (add as many agents as makes sense), and it will take a long time to fill up the context. The agents get fresh context, and you get to manage explicitly what information is allowed to flow between them. It also tends to mean it is a lot easier to introduce quality gates - eg. your testing agent and your code review agent etc. will not decide they can skip testing because they "know" they implemented things correctly, because there is no memory of that in their context.

Sometimes too much knowledge is a bad thing.

hereme888 7 hours ago
why would it be? It's a creative setup.
ggoo 7 hours ago
I just actually can't tell, it reads like satire to me.
blibble 5 hours ago
to me, it reads like mental illness
mafriese 5 hours ago
maybe it's a mix of both :)
PradeetPatel 6 hours ago
Why would it be satire? I thought that's a pretty stranded Agentic workflows.

My current workplace follows a similar workflow. We have a repository full of agent.md files for different roles and associated personas.

E.g. For project managers, you might have a feature focused one, a delivery driven one, and one that aims to minimise scope/technology creep.

ionwake 6 hours ago
I mean no offence to anyone but whenever new tech progresses rapidly it usually catches most unaware, who tend to ridicule or feel the concepts are sourced from it.
blibble 5 hours ago
yeah, nfts, metaverse, all great advances

same people pushing this crap

jitl 4 hours ago
ai is actually useful tho. idk about this level of abstraction but the more basic delegation to one little guy in the terminal gives me a lot of extra time
ggregoryarms 3 hours ago
Maybe that's because you're not using your time well in the first place
ionwake 5 hours ago
bro im using ai swarms, have you even tried them?
blibble 4 hours ago
bro wanna buy some monkey jpegs?

100% genuine

ionwake 4 hours ago
Your mocking NFTs. but the original NFT cyberpunks still sell for a minimum of $80k.

Where were you back then? Laughing about them instead of creating intergenerational wealth for a few bucks?

blibble 3 hours ago
> Laughing about them instead of creating intergenerational wealth for a few bucks?

it's not creating wealth, it's scamming the gullible

criminality being lucrative is not a new phenomenon

lupire 3 hours ago
Are you sure that yours would sell for $80K, if you aren't using it to launder money with your criminal associates?
SkyPuncher 3 hours ago
Doubt it. I use a similar setup from time to time.

You need to have different skills at different times. This type of setup helps break those skills out.

thaynt 4 hours ago
I think many people really like the gamification and complex role playing. That is how GitHub got popular, that is how Rube Goldberg agent/swarm/cult setups get popular.

It attracts the gamers and LARPers. Unfortunately, management is on their side until they find out after four years or so that it is all a scam.

krackers 4 hours ago
I've heard some people say that "vibe coding" with chatbots is like slot machines, you just keep "propmting" until you hit the jackpot. And there was some earlier study that people _felt_ more productive even if they weren't (caveat that this was with older models), which aligns with the sort of time-dilation people feel when gambling.

I guess "agentic swarms" are the next evolution of the meta-game, the perfect nerd-sniping strategy. Now you can spend all your time minmaxing your team, balancing strengths/weaknesses by tweaking subagents, adding more verifiers and project managers. Maybe there's some psychological draw, that people can feel like gods and have a taste of the power execs feel, even though that power is ultimately a simulacra as well.

theonething 6 hours ago
I don't think so.
raffraffraff 6 hours ago
The next stage in all of this shit is to turn what you have into a service. What's the phrase? I don't want to talk to the monkey, I want to talk to the organ grinder. So when you kick things off it should be a tough interview with the manager and program manager. Once they're on board and know what you want, they start cracking. Then they just call you in to give demos and updates. Lol
heliumtera 5 hours ago
Congratulations on coming up with the cringiest thing I have ever seen. Nothing will top this, ever.

Corporate has to die

justmedep 4 hours ago
Scrum masters typically do not assign tickets.
joshribakoff 12 hours ago
This is just sub agents, built into Claude. You don’t need 300,000 line tmux abstractions written in go. You just tell Claude to do work in parallel with background sub agents. It helps to have a file for handing off the prompt, tracking progress, and reporting back. I also recommend constraining agents to their own worktrees. I am writing down the pattern here https://workforest.space while nearly everyone is building orchestrators i also noticed claude is already the best orchestrator for claude.
skippyboxedhero 9 hours ago
It isn't sub agents. The gap with existing tooling is that the abstraction is over a task rather than a conversation (due to the issue with third-party apps, Claude Code has been inherently limited to conversations which is why they have been lacking in this area, Claude Code Web was the first move in this direction), and the AI is actually coordinating the work (as opposed to being constantly prompted by the user).

One of the issues that people had which necessitated this feature is that you have a task, you tell Claude to work on it, and Claude has to keep checking back in for various (usually trivial) things. This workflow allows for more effective independent work without context management issues (if you have subagents, there is also an issue with how the progress of the task is communicated by introducing things like task board, it is possible to manage this state outside of context). The flow is quite complex and requires a lot of additional context that isn't required with chat-based flow, but is a much better way to do things.

The way to think about this pattern - one which many people began concurrently building in the past few months - is an AI which manages other AIs.

vidarh 7 hours ago
It isn't "just" sub agents, but you can achieve most of this just with a few agents that take on generic roles, and a skill or command that just tells claude to orchestrate those agents, and a CLAUDE.md that tells it how to maintain plans and task lists, and how to allow the agents to communicate their progress.

It isn't all that hard to bootstrap. It is, however, something most people don't think about and shouldn't need to have to learn how to cobble together themselves, and I'm sure there will be advantages to getting more sophisticated implementations.

skippyboxedhero 6 hours ago
Right, but the model is still: you tell the AI what to do, this is the AI tells other AIs what to do. The context makes a huge difference because it has to be able to run autonomously. It is possible to do this with SDK and the workflow is completely different.

It is very difficult to manage task lists in context. Have you actually tried to do this? i.e. not within a Claude Code chat instance but by one-shot prompting. It is possible that they have worked out some way to do this, but when you have tens of tasks, merge conflicts, you are running that prompt over months, etc. At best, it doesn't work. At worst, you are burning a lot of tokens for nothing.

It is hard to bootstrap because this isn't how Claude Code works. If you are just using OpenRouter, it is also not easy because, after setting up tools/rebuilding Claude Code, it is very challenging to setup an environment so the AI can work effectively, errors can be returned, questions returned, etc. Afaik, this is basically what Aider does...it is not easy, it is especially not easy in Claude Code which has a lot of binding choices from the business strategy that Anthropic picked.

vidarh 5 hours ago
> Have you actually tried to do this? i.e. not within a Claude Code chat instance but by one-shot prompting.

You ask if I've tried to do this, and then set constraints that are completely different to what I described.

I have done what I described. Several times for different projects. I have a setup like that running right now in a different window.

> It is hard to bootstrap because this isn't how Claude Code works.

It is how Claude Code works when you give it a number of sub-agents with rules for how to manage files that effectively works like task queues, or skills/mcp servers to interact with communications tools.

> it is not easy

It is not easy to do in a generic way that works without tweaks for every project and every user. It is reasonably easy to do for specific teams where you can adjust it to the desired workflows.

ukuina 5 hours ago
It's natural to assume that subagents will scale to the next level of abstraction; as you mentioned, they do not.

The unlock here is tmux-based session management for the teammates, with two-way communication using agent inbox. It works very well.

adastra22 7 hours ago
> Claude Code has been inherently limited to conversations

How so? I’ve been using “claude -p” for a while now.

But even within an interactive session, an agent call out is non-interactive. It operates entirely autonomously, and then reports back the end result to the top level agent.

skippyboxedhero 7 hours ago
Because of OAuth. If they gave people API keys then no-one buys their ludicrously priced API product (I assume their strategy is to subsidise their consumer product with the business product).

You can use Claude Code SDK but it requires a token from Claude Code. If you use this token anywhere else, your account gets shut down.

Claude -p still hits Claude Code with all the tools, all the Claude Code wrapping.

adastra22 4 hours ago
That’s not what this subthread is about. They’re talking about the subagent within Claude Code itself.

Btw, you can use the Claude Agent SDK (the renamed Claude Code SDK) with a subscription. I can tell you it works out of the box, and AFAIK it is not a ToS violation.

mmcclure 14 minutes ago
Oh really? I was looking at the Agent SDK for an idea and the docs seemed to imply that wasn't the case.

    Unless previously approved, we do not allow third party developers to offer Claude.ai login or rate limits for their products, including agents built on the Claude Agent SDK. Please use the API key authentication methods described in this document instead.
I didn't dig deeper, but I'd pick it back up for a little personal project if I could just use my current subscription. Does it just use your local CC session out of the box?
tobyjsullivan 6 hours ago
I believe they’re talking about Claude Code’s built-in agents feature which works fine with a Max subscription.

https://code.claude.com/docs/en/sub-agents

Are you talking about the same thing or something else like having Claude start new shell sessions?

TeMPOraL 5 hours ago
> If they gave people API keys then no-one buys their ludicrously priced API product

The main driver for those subscriptions is that their monthly cost with Opus 3.7 and up pays itself back in couple hours of basic CC use, relative to API prices.

blibble 5 hours ago
can't you just rip the oauth client secret out of the code?
stingraycharles 11 hours ago
It’s even less of a feature, Claude Code already has subagents; this new feature just ensures Claude Code actually uses this for implementation.

imho the plans of Claude Code are not detailed enough to pull this off; they’re trying to do it to preserve context, but the level of detail in the plans is not nearly enough for it to be reliable.

ctoth 8 hours ago
I agree with this. Any time I make a plan I have to go back and fill it in, fill it in, what did we miss, tdd, yada yada. And yes, I have all this stuff in CLAUDE.md.

You start to get a sense for what size plan (in kilobytes) corresponds to what level of effort. Verification adds effort, and there's a sort of ... Rocket equation? in that the more infrastructure you put in to handle like ... the logistics of the plan, the less you have for actual plan content, which puts a cap on the size of an actionable plan. If you can hit the sweet spot though... GTFO.

I also like to iterate several times in plan mode with Claude before just handing the whole plan to Codex to melt with a superlaser. Claude is a lot more ... fun/personable to work with? Codex is a force of nature.

Another important thing I will do is now that launching plans clear context, it's good to get out of planning mode early, hit an underspecified bit, go back into planning mode and say something like "As you can see the plan was underspecified, what will the next agent actually need to succeed?" and iterate that way before we actually start making moves. This is made possible by lots of explicit instructions in CLAUDE.md for Claude to tell me what it's planning/thinking before it acts. Suppressing the toolcall reflex and getting actual thought out helps so much.

tobyjsullivan 6 hours ago
It’s moving fast. Just today I noticed Claude Code now ends plans with a reference to the entire prior conversation (as a .jsonl file on disk) with instructions to check that for more details.

Not sure how well it’s working though (my agents haven’t used it yet)

dceddia 10 hours ago
Interesting about the level of detail. I’ve noticed that myself but I haven’t done much to address it yet.

I can imagine some ideas (ask it for more detail, ask it to make a smaller plan and add detail to that) but I’m curious if you have any experience improving those plans.

stingraycharles 9 hours ago
I’m trying to solve this myself by implementing a whole planner workflow at https://github.com/solatis/claude-config

Effectively it tries to resolve all ambiguities by making all decisions explicit — if the source cannot be resolved to documentation or anything, it’s asked to the user.

It also tries to capture all “invisible knowledge” by documenting everything, so that all these decisions and business context are captured in the codebase again.

Which - in theory - should make long term coding using LLMs more sane.

The downside is that it takes 30min - 60min to write a plan, but it’s much less likely to make silly choices.

vardalab 7 hours ago
I iterate around issues. I have a skill to launch a new tmux window for worktree with Claude in one pane and Codex in another pane with instructions on which issue to work on, Claude has instructions to create a plan, while Codex has instructions to understand the background information necessary for this issue to be worked on. By the time they're both done, then I can feed Claude's plan into Codex, and Codex is ready to analyze it. And then Codex feeds the plan back to Claude, and they kind of ping pong like that a couple times. And after a certain or several iterations, there's enough refinement that things usually work. Then Claude clears context and executes the plan. Then Codex reviews the commit and it still has all the original context so it knows what we have been planning and what the research was about the infrastructure. And it does a really good job reviewing. And again, then they ping pong back and forth a couple times, and the end product is pretty decent. Codex's strength is that it really goes in-depth. I usually do this at a high reasoning effort. But Codex has zero EQ or communication skills, so it works really well as a pedantic reviewer. Claude is much more pleasant to interact with. There's just no comparison. That's why I like planning with Claude much more because we can iterate.. I am just a hobbyist though. I do this to run my Ansible/Terraform infrastructure for a good size homelab with 10 hosts. So we actually touch real hardware a lot and there's always some gotchas to deal with. But together, this is a pretty fun way to work. I like automating stuff, so it really scratches that itch.
colelyman 8 hours ago
I have had good success with the plans generated by https://github.com/obra/superpowers I also really like the Socratic method it uses to create the plans.
AffableSpatula 12 hours ago
Claude already had subagents. This is a new mode for the main agent to be in (bespoke context oriented to delegation), combined with a team-oriented task system and a mailbox system for subagents to communicate with each other. All integrated into the harness in a way that plugins can't achieve.
theturtletalks 9 hours ago
Wow there goes a lot of harnesses out the window. The main limitation of subagents was they couldn’t communicate back and forth with the main agent. How do we invoke swarm mode in Claude Code?
apsurd 10 hours ago
OT: Your visual on "stacked PRs" instantly made me understand what a stacked PR is. Thank you!

I had read about them before but for whatever reason it never clicked.

Turns out I already work like this, but I use commits as "PRs in the stack" and I constantly try to keep them up to date and ordered by rebasing, which is a pain.

Given my new insight with the way you displayed it, I had a chat with chatGPT and feel good about giving it a try:

    1. 2-3 branches based on a main feature branch
    2. can rebase base branch with same frequency, just don't overdo it, conflicts should be base-isolated.
    3. You're doing it wrong if conflicts cascade deeply and often
    4. Yes merge order matters, but tools can help and generally the isolation is the important piece
abhinavg 6 hours ago
If you’re interested in exploring tooling around stacked PRs, I wrote git-spice (https://abhinav.github.io/git-spice/) a while ago. It’s free and open-source, no strings attached.
Griffinsauce 9 hours ago
If you're rebasing a lot, definitely set up rerere (reuse recorded solution) - it improves things enormously.

Do make sure you know how to reset the cache, in case you did a bad conflict resolution because it will keep biting you. Besides that caveat it's a must.

byproxy 9 hours ago
apsurd 9 hours ago
After a quick read it seems like gitflow is intended to model a release cycle. It uses branches to coordinate and log releases.

Stacking is meant to make development of non-trivial features more manageable and more likely to enter main safer and faster.

it's specific to each developer's workflow and wouldn't necessarily produce artifacts once merged into main (as gitflow seems to intentionally have a stance on)

withinboredom 9 hours ago
Please don’t use git-flow. Every time I see it, it looks like an over-engineer’s wet dream.
seff 9 hours ago
Can you say more as to why? The concept is not complex and in our situation at least provides a lot of benefits.
jdxcode 8 hours ago
I think the guy that created it has even stated he thinks it's a bad idea
withinboredom 8 hours ago
Literally the reason’s for git’s existence is to make merging diverging histories less complicated. Adding back the complexity misses the point entirely.
mkw5053 10 hours ago
Yeah, since they introduced (possibly async) subagents, I've had my main claude instance act as a manager overseeing implementation agents, keeping it's context clean, and ensuring everything goes to plan in the highest quality way.
AffableSpatula 10 hours ago
yep this is exactly how I use the main agent too, I explicitly instruct to only ever use background async subagents. Not enough people understand that the claude code harness is event driven now and will wake up whenever these subagent completion events happen.
bradgessler 9 hours ago
Any recommendations on sandboxing agents? Last time I asked folks recommended docker.
ahstilde 1 hour ago
skybrian 9 hours ago
I like running remotely using exe.dev with SyncThing to sync files to my laptop.

I use Shelley (their web-based agent) but they have Claude Code installed too.

daxfohl 8 hours ago
I want it to generate better code but less of it, and be more proactive about getting human feedback before it starts going off the rails. This sounds like an inexorable push in the opposite direction.

I can see this approach being useful once the foundation is more robust, has better common sense, knows when to push back when requirements conflict or are underspecified. But with current models I can only see this approach as exacerbating the problem; coding agents solution is almost always "more code", not less. Makes for a nice demo, but I can't imagine this would build anything that wouldn't have huge operational problems and 10x-100x more code than necessary.

mtalantikite 5 hours ago
Agreed, I'm constantly coming back to a Claude tmux pane just to see it's decided to do something completely ridiculous. Just the other day I was having it add some test coverage stats to CI runs and when I came back it was basically trying to reinvent Istanbul in a bash script because the nyc tool wasn't installed in CI. I had to interrupt it and say "uh, just install nyc?". I was "Absolutely right!".
spondyl 2 hours ago
> it was basically trying to reinvent Istanbul in a bash script because the nyc tool wasn't installed in CI

For the first part of this comment, I thought "trying to reinvent Istanbul in a bash script" was meant to be a funny way to say "It was generating a lot of code" (as in generating a city's worth of code)

xyzsparetimexyz 4 hours ago
If only Rome could be built in a day..
sothatsit 7 hours ago
They haven’t released this feature, so maybe they know the models aren’t good enough yet.

I also think it’s interesting to see Anthropic continue to experiment at the edge of what models are capable of, and having it in the harness will probably let them fine-tune for it. It may not work today, but it might work at the end of 2026.

daxfohl 6 hours ago
True, though even then I kind of wonder what's the point. Once they build an AI that's as good as a human coder but 1000x faster, parallelization no longer buys you anything. Writing and deploying the code is no longer the bottleneck, so the extra coordination required for parallelism seems like extra cost and risk with no practical benefit.
sothatsit 5 hours ago
Each agent having their own fresh context window for each task is probably alone a good way to improve quality. And then I can imagine agents reviewing each others work might work to improve quality as well, like how GPT-5 Pro improves upon GPT-5 Thinking.
nojs 5 hours ago
It’s more about context management, not speed
xyzsparetimexyz 4 hours ago
Do you really need a full dev team ensemble to manage context? Surely subagents are enough.
TeMPOraL 3 hours ago
Potato, potatoh. People get confused by all this agent talk and forget that, at the end of the day, LLM calls are effectively stateless. It's all abstractions around how to manage the context you send with each request.
lupire 3 hours ago
All you have to do is set up an MCP that routes to a human on the backend, and you d got an AI that asks for human feedback.

Antigravity and others already ask for human feedback on their plans.

replwoacause 3 hours ago
I've done plenty of vibe coding even though I know how to program but I mostly work with a single agent through its CLI. The progress is really good and more importantly, I can follow it. I can read the output, test it, and understand what changed and why. I don't see much upside in swarms. But I do see the downside which is losing the ability to keep the whole system in my head. The codebase starts growing in directions I didn't choose and it seems decisions will get made I didn't review. Early AI autocomplete that could finish a function already felt like a big productivity win and then AI that could write whole files was an even bigger jump. Like pretty massive. Running one agent at a time, watching what it does, and vetting the output still works well for me and still feels like a strong multiplier. But now there's so much more ceremony: AGENTS.md, SKILLS.md, delegation frameworks. I guess I'm not convinced that leads to better outcomes but I'm probably missing something. It just seems like a tradeoff that sacrifices understanding for ostensible progress.
birken 10 hours ago
I'd really like to see a regular poll on HN that keeps track of which AI coding agents are the most popular among this community, like the TIOBE Index for programming languages.

Hard to keep up with all the changes and it would be nice to see a high level view of what people are using and how that might be shifting over time.

samsolomon 10 hours ago
Not this community's opinion on agents, but I've found it helpful to check the lmarena leaderboards occasionally. Your comment prompted me to take a look for the first time in a while. Kind of surprising to see models like MiniMax 2.1 above most of the OpenAI GPTs.

https://lmarena.ai/leaderboard/code

Also, I'm not sure if it's exactly the case but I think you can look at throughput of the models on openrouter and get an idea of how fast/expensive they are.

https://openrouter.ai/minimax/minimax-m2.1

7 hours ago
7777777phil 9 hours ago
I just started something like that, haven’t shared it widely yet, but here we go - happy if you participate: https://agentic-coding-survey.pages.dev/
danjl 9 hours ago
Add vscode. Add a list of models, since many tools allow you to select which model you use.
7777777phil 8 hours ago
Thanks for the feedback. I thought there are just too many models and versions to list them all. For now, if you select "other" you get a text field to add any model not listed, hope this helps.
hmottestad 9 hours ago
You should add OpenAI Codex CLI.
7777777phil 8 hours ago
Thanks for the feedback, I'll do that. For now, if you select "other" you get a text field to add any model not listed..
Kerrick 6 hours ago
Any chance you'll add Antigravity and Jetbrains Junie? I've been using almost nothing but those for the last month. Antigravity at home, Junie at work.
7777777phil 6 hours ago
Done, upon popular demand I added Antigravity, Codex CLI, and Junie
Kerrick 6 hours ago
Thanks!

> Q5. For which tasks do you use AI assistance most?

This is really tough for me. I haven't done a single one of those mostly-manually over the last month.

mudkipdev 4 hours ago
Just pick your favorite one and stick with it. There is no point in keeping up, since we're in an endless cycle of hype where is one ranked higher than the other, with them eventually catching up to each other
morley 7 hours ago
I personally don't want to trawl through Twitter to find the current state-of-the-art, so I read Zvi Mowshowitz's newsletter:

https://thezvi.substack.com/

His newsletter put me onto using Opus 4.5 exclusively on Dec 1, a little over a week after it was released. That's pretty good for a few minutes of reading a week.

xyzsparetimexyz 4 hours ago
Christ, the latest post is about dating and uses an ai generated wojak meme..
nikcub 7 hours ago
I have an agent skill that is currently in the top 10 or so of the skills.sh directory - in terms of that audience, it's about 80% claude code.

Also 75% darwin-arm64

3 hours ago
fragmede 9 hours ago
Question is, are people on HN procrastinating and commenting here because the agent isn't very good and they're avoiding having to write the code themselves, or is the agent so good that it's off writing code, and the people here are commenting out of boredom?
thevinter 9 hours ago
You're making it sound like before agents existed HN was a ghost town because everyone was too busy building ImportantThingTM by hand
fragmede 8 hours ago
Oh. Surely you know this forum didn't exist pre-ChatGPT. Everything in the archives was generated so it just looks that way.
nonethewiser 9 hours ago
>Question is, are people on HN procrastinating and commenting here because the agent isn't very good and they're avoiding having to write the code themselves

Can you help me envision what you're saying? It's async - you will have to wait whether its good or not. And in theory the better it is the more time you'd have to comment here, right?

fragmede 8 hours ago
I'm saying if it's that bad, then it's pure procrastination
g947o 7 hours ago
People have been procrastinating on HN since the beginning of time, before coding agents existed.
fragmede 5 minutes ago
Correct me if I'm wrong, but before ChatGPT, there was fewer comments about vibecoding.
8 hours ago
ramoz 9 hours ago
When all of industry is trying to catch up with the features of one coding agent - it may be a signal to just use that one.
anhner 4 hours ago
Sure, let's all ditch linux and macOS as well since they're not the most popular...
coldtea 8 hours ago
>You're not talking to an AI coder anymore. You're talking to a team lead. The lead doesn't write code - it plans, delegates, and synthesizes.

They couldn't even be bothered to write the Tweet themselves...

mrtesthah 7 hours ago
isn’t it interesting how often this rhetorical construction is overused by AI?
TeMPOraL 5 hours ago
Partly because it's a good construct. Most people's writing is garbage compared to what LLMs output by default.

But the other part of it is, each conversation you have, and each piece of AI output you read online, is written by LLM instance that has no memory of prior conversations, so it doesn't know that, from human perspective, it used this construct 20 times in the last hour. Human writers avoid repeating the same phrases in quick succession, even across different writings (e.g. I might not reuse some phrase in email to person A, because I just used it in email to unrelated person B, and it feels like bad style).

Perhaps that's why reading LLM output feels like reading high school essays. Those essays all look alike because they're all written independently and each is a self-contained piece where the author tries to show off their mastery of language. After reading 20 of them in a row, one too gets tired of seeing the same few constructs being used in nearly every one of them.

bangaladore 7 hours ago
Very much so. It feels like it can't have been that common in the original training corpus. Probably more common now given that we are training slop generators with slop.
czhu12 10 hours ago
The problem I’ve been having is that when Claude generates copious amounts of code, it makes it way harder to review than small snippets one at a time.

Some would argue there’s no point reviewing the code, just test the implementation and if it works, it works.

I still am kind of nervous doing this in critical projects.

Anyone just YOLO code for projects that’s not meant to be one time, but fully intend to have to be supported for a long time? What are learnings after 3-6 months of supporting in production?

serial_dev 10 hours ago
In a professional setting where you still have coding standards, and people will review your code, and the code actually reaches hundreds of thousands of real users, handling one agent at a time is plenty for me. The code output is never good enough, and it makes up stuff even for moderately complicated debugging ("Oh I can clearly see the issue now", I heard it ten times before and you were always wrong!)

I do use them, though, it helps me, search, understand, narrow down and ideate, it's still a better Google, and the experience is getting better every quarter, but people letting tens or hundreds of agents just rip... I can't imagine doing it.

For personal throwaway projects that you do because you want to reach the end output (as opposed to learning or caring), sure, do it, you verify it works roughly, and be done with it.

pron 8 hours ago
This is my problem with the whole "can LLMs code?" discussion. Obviously, LLMs can produce code, well even, much like a champion golfer can get a hole in one. But can they code in the sense of "the pilot can fly the plane", i.e. barring a catastrophic mechanical malfunction or a once-in-a-decade weather phenomennon, the pilot will get the plane to its destination safely? I don't think so.

To me, someone who can code means someone who (unless they're in a detectable state of drunkenness, fatigue, illness, or distraction) will successfully complete a coding task commensurate with some level of experience or, at the very least, explain why exactly the task is proving difficult. While I've seen coding agents do things that truly amaze me, they also make mistakes that no one who "can code" ever makes. If you can't trust an LLM to complete a task anyone who can code will either complete or explain their failure, then it can't code, even if it can (in the sense of "a flipped coin can come up heads") sometimes emit impressive code.

lupire 3 hours ago
That's a funny analogy. You should look into how modern planes are flown. Hint: it's a computer.
pron 3 hours ago
> Hint: it's a computer.

Not quite, but in any event none of the avionics is an LLM or a program generated by one.

prmoustache 7 hours ago
> people will review your code,

People will ask LLM to review some slop made by LLM and they will be absolutely right!

There is no limit to lazyness.

flemhans 5 hours ago
Soon you'll be seen as irresponsible and wasteful if you don't let the smarter LLM do it.
KaiserPro 9 hours ago
> people will review your code,

I mean you'd think. But it depends on the motivations.

At meta, we had league tables for reviewing code. Even then people only really looked at it if a) they were a nitpicking shit b) don't like you and wanted piss on your chips c) its another team trying to fix our shit.

With the internal claude rollout and the drive to vibe code all the things, I'm not sure that situation has got any better. Fortunately its not my problem anymore

serial_dev 8 hours ago
Well, it certainly depends on the culture of the team and organization.

Where you have shared ownership, meaning once I approved your PR, I am just as responsible of something goes wrong as you are and I can be expected to understand it just as well as you do… your code will get reviewed.

If shipping is the number one priority of the team, and a team is really just a group of individuals working to meet their quota, and everyone wants to simply ship their stuff, managers pressure managers to constantly put pressure on the devs, you’ll get your PR rubber stamped after 20s of review. Why would I spend hours trying to understand what you did if I could work on my stuff.

And yes, these tools make this 100x worse, people don’t understand their fixes, code standards are no longer relevant, and you are expected to ship 10x faster, so it’s all just slop from here on.

gen220 10 hours ago
In my (admittedly conflict-of-interest, I work for graphite/cursor) opinion, asking CC to stack changes, and then having an automated reviewer agent help a lot with digesting and building conviction in otherwise-large changesets.

My "first pass" of review is usually me reading the PR stack in graphite. I might iterate on the stack a few times with CC before publishing it for review. I have agents generate much of my code, but this workflow has allowed me to retain ownership/understanding of the systems I'm shipping.

AstroBen 10 hours ago
I think we'll start to see the results of that late this year, but it's a little early yet. Plenty of people are diving headfirst into it

To me it feels like building your project on sand. Not a good idea unless it's a sandcastle

linsomniac 8 hours ago
I have Claude Code author changes, and then I use this "codex-review" skill I wrote that does a review of the last commit. You might try asking Codex (or whatever) to review the change to give you some pointers to focus on with your review, and also in your review you can see if Codex was on track or if it missed anything, maybe feed that back into your codex review prompt.
10 hours ago
idontwantthis 10 hours ago
I just can’t get with this. There is so much beyond “works” in software. There are requirements that you didn’t know about and breaking scenarios that you didn’t plan for and if you don’t know how the code works, you’re not going to be able to fix it. Assuming an AI could fix any problem given a good enough prompt, I can’t write that prompt without sufficient knowledge and experience in the codebase. I’m not saying they are useless, but I cannot just prompt, test and ship a multiservice, asynchronous, multidb, zero downtime app.
zmmmmm 5 hours ago
Yes this is one of my concerns.

Usually about 50% of my understanding of the domain comes from the process of building the code. I can see a scenario where large scale automated code works for a while but then quickly becomes unsupportable because the domain expertise isn't there to drive it. People are currently working off their pre-existing domain knowledge which is what allows them to rapidly and accurately express in a few sentences what an AI should do and then give decisive feedback to it.

The best counter argument is that AIs can explain the existing code and domain almost as well as they can code it to begin with. So there is a reasonable prospect that the whole system can sustain itself. However there is no arguing to me that isn't a huge experiment. Any company that is producing enormous amounts of code that nobody understands is well out over their skis and could easily find themselves a year or two down the track with huge issues.

atonse 8 hours ago
I don’t know what your stack is, but at least with elixir and especially typescript/nextJS projects, and properly documenting all those pieces you mentioned, it goes a long way. You’d be amazed.
idontwantthis 6 hours ago
If it involves Nextjs then we aren’t talking about the same category of software. Yes it can make a website pretty darn well. Can it debug and fix excessive database connection creation in a way that won’t make things worse? Maybe, but more often not and that’s why we are engineers and not craftsmen.

That example is from a recent bug I fixed without Cursor being able to help. It wanted to create a wrapper around the pool class that would have blocked all threads until a connection was free. Bug fixed! App broken!

mrtesthah 7 hours ago
I would never use, let alone pay for, a fully vibe-coded app whose implementation no human understands.

Whether you’re reading a book or using an app, you’re communicating with the author by way of your shared humanity in how they anticipate what you’re thinking as you explore the work. The author incorporates and plans for those predicted reactions and thoughts where it makes sense. Ultimately the author is conveying an implicit mental model to the reader.

The first problem is that many of these pathways and edge cases aren’t apparent until the actual implementation, and sometimes in the process the author realizes that the overall app would work better if it were re-specified from the start. This opportunity is lost without a hands on approach.

The second problem is that, the less human touch is there, the less consistent the mental model conveyed to the user is going to be, because a specification and collection of prompts does not constitute a mental model. This can create subconscious confusion and cognitive friction when interacting with the work.

andrekandre 2 hours ago

  > The second problem is that, the less human touch is there, the less consistent the mental model conveyed to the user is going to be, because a specification and collection of prompts does not constitute a mental model. This can create subconscious confusion and cognitive friction when interacting with the work.
tbf, this is a trend i see more and more across the industry; llm or not so many process get automated that teams just implement x cause pdm y said so and its because they need to meet goal z for the quarter... and everyone is on scrum autopilot they cant see the forest for the trees anymore.

i feel like the massive automation afforded by these coding agents may make this worse

chasing 7 hours ago
Yeah, it's not just my job to generate the code: It's my job to know the code. I can't let code out into the wild that I'm not 100% willing to vouch for.
zmmmmm 5 hours ago
At a higher level, it goes beyond that. It's my job to take responsibility for code. At some fundamental level that puts a limit on how productive AI can be. Because we can only produce code as fast as responsibility takers can execute whatever processes they need to do to ensure sufficient due diligence is executed. In a lot of jurisdictions, human-in-loop line by line review is being mandated for code developed in regulatory settings. That pretty much caps the output at the rate of human review, which is to be honest, not drastically higher than coding itself anyway (Often I might invest 30% of the time to review a change as the developer took to do it).

It means there is no value in producing more code. Only value in producing better, clearer, safer code that can be reasoned about by humans. Which in turn makes me very sceptical about agents other than as a useful parallelisation mechanism akin to multiple developers working on separate features. But in terms of ramping up the level of automation - it's frankly kind of boring to me because if anything it make the review part harder which actually slows us down.

yeasku 4 hours ago
[dead]
szundi 10 hours ago
[dead]
Androider 12 hours ago
Looks like agent orchestrators provided by the foundation model providers will become a big theme in 2026. By wrapping it in terms that are already used in software development today like team leads, team members, etc. rather than inventing a completely new taxonomy of Polecats and Badgers, will help make it more successful and understandable.
bloppe 11 hours ago
Respectfully disagree. I think polecats are a reasonable antidote to overanthropomorphization.
qdot76367 9 hours ago
Furries would like to have a word.
MrOrelliOReilly 7 hours ago
Totally agreed. Most the weird concepts of Gas Town are just workarounds for bad behavior in Claude or the underlying models. Anthropic is in the best position to get their own model to adhere to orchestration steps, obviating the need for these extra layers. Beyond that, there shouldn’t actually be much to orchestration beyond a solid messaging and task management implementation.
wild_pointer 13 hours ago
Listen team lead and the whole team, make this button red.
brookst 12 hours ago
Principal engineers! We need architecture! Marketing team, we need ads with celebrities! Product team, we need a roadmap to build on this for the next year! ML experts, get this into the training and RL sets! Finance folks, get me annual forecasts and ROI against WACCC! Ops, we’ll need 24/7 coverage and a guarantee of five nines. Procurement, lock down contracts. Alright everyone… make this button red!
simultsop 6 hours ago
We have to reject claude can do it simply by a prompt, then everyone can do it. As SWE's we are not going to pragmatically accept we are done. https://www.youtube.com/watch?v=g_Bvo0tsD9s
AffableSpatula 13 hours ago
ha! The default system prompt appears to give the main agent appropriate guidance about only using swarm mode when appropriate (same as entering itself into plan mode). You can further prompt it in your own CLAUDE.md to be even more resistant to using the mode if the task at hand isn't significant enough to warrant it.
vorticalbox 10 hours ago
I like opencode for the fact I can switch between build and plan mode just by pressing tab.
thevinter 9 hours ago
Isn't it the same in base claude-code?
bigiain 1 hour ago
So this is Gas Town, just without the "Steve Yegge makes a quarter of a million on a memecoin pump-n-dump" step (yet)?
hmokiguess 1 hour ago
Am I the only one who’s been so late to crypto? I still have not touched a single cryptocurrency, even somewhat stable/legit ones. It always gives me a bit of FOMO hearing these stories
neom 13 hours ago
Claude Code in the desktop app seems to do this? It's crazy to watch. It sets of these huge swarms of worker readers under master task headings, that go off and explore the code base and compile huge reports and todo lists, then another system behind the scenes seems to be compiling everything to large master schemas/plans. I create helper files and then have a devops chat, a front end chat, an architecture chat and a security chat, and once each it done it's work it automatically writes to a log and the others pick up the log (it seems to have a system reminder process build in that can push updates from other chats into other chats. It's really wild to watch it work, and it's very intuitive and fun to use. I've not tried CLI claude code only claude code in the desktop app, but desktop app sftp to a droplet with ssh for it to use the terminal is a very very interesting experience, it can seem to just go for hours building, fixing, checking it's own work, loading it's work in the browser, doing more work etc all on it's own - it's how I built this: https://news.ycombinator.com/item?id=46724896 in 3 days.
jswny 12 hours ago
That’s just spawning multiple parallel explore agents instructed to look at different things, and then compiling results

That’s a pretty basic functionality in Claude code

neom 12 hours ago
Sounds like I should probably switch to claude code cli. Thanks for the info. :)
esperent 3 hours ago
I added tests to an old project a few days ago. I spent a while to carefully spec everything out, and there was a lot of tedious work. Aiming for 70% coverage meant that a few thousand unit tests were needed.

I wrote up a technical plan with Claude code and I was about to set it to work when I thought, hang on, this would be very easy to split into separate work, let's try this subagent thing.

So I asked Claude to split it up into non- overlapping pieces and send out as many agents as it could to work on each piece.

I expected 3 or 4. It sent out 26 subagents. Drudge work that I estimate would have optimistically taken me several months was done in about 20 minutes. Crazy.

Of course it still did take me a couple of days to go through everything and feel confident that the tests were doing their job properly. Asking Claude to review separate sections carefully helped a lot there too. I'm pretty confident that the tests I ended up with were as good as what I would have written.

sbsnjsks 11 hours ago
[dead]
deaux 12 hours ago
Sounds very similar to oh-my-opencode.
tiberriver256 9 hours ago
We call it Shawarma where I come from
nehalem 13 hours ago
Answering the question how to sell more tokens per customer while maintaining ~~mediocre~~ breakthrough results.
AffableSpatula 13 hours ago
Delegation patterns like swarm lead to less token usage because:

1. Subagents doing work have a fresh context (ie. focused and not working on the top of a larger monolithic context) 2. Subagents enjoying a more compact context leads to better reasoning, more effective problem solving, less tokens burned.

nulone 12 hours ago
Merge cost kills this. Does the harness enforce file/ownership boundaries per worker, and run tests before folding changes back into the lead context?
AffableSpatula 12 hours ago
I don't know what you're referring to but I can say with confidence that I see more efficient token usage from a delegated approach, for the reasons I stated, provided that the tasks are correctly sized. ymmv of course :)
Blemiono 13 hours ago
[dead]
basedrum 12 hours ago
How is this different from GSD: https://github.com/glittercowboy/get-shit-done

I've been using that and it's excellent

nonethewiser 9 hours ago
GSD was the first project management framework I used. Initially I loved it because it felt like I was so much better organized.

As time went on I felt like the organization was kind of an illusion. It demanded something from me and steered Claude, but ultimately Claude is doing whatever it's going to do.

I went black to just raw-dogging it with lots of use of planning mode.

djfdat 11 hours ago
Really boils down to the benefits of first party software from a company that has billions of dollars of funding vs similar third party software from an individual with no funding.

GSD might be better right now, but will it continue to be better in the future, and are you willing to build your workflows around that bet?

ramoz 9 hours ago
I dont understand these questions/references. It's different because it's a capability baked into the actual tool and maintained by the originators of the tool.
AffableSpatula 12 hours ago
a similar question was asked elsewhere in the thread; the difference is that this is tightly integrated into the harness
RockRobotRock 3 hours ago
svara 12 hours ago
I'm a fan of AI coding tools but the trend of adding ever more autonomy to agents confuses me.

The rate at which a person running these tools can review and comprehend the output properly is basically reached with just a single thread with a human in the loop.

Which implies that this is not intended to be used in a setting where people will be reading the code.

Does that... Actually work for anyone? My experience so far with AI tools would have me believe that it's a terrible idea.

ttul 10 hours ago
Yes, this actually works. In 2026, software engineering is going to change a great deal as a result, and if you're not at least experimenting with this stuff to learn what it's capable of, that's a red flag for your career prospects.

I don't mean this in a disparaging way. But we're at a car-meets-horse-and-buggy moment and it's happening really quickly. We all need to at least try driving a car and maybe park the horse in the stable for a few hours.

xyzsparetimexyz 4 hours ago
The FOMO nonsense is really uncalled for. If everything is going to be vibecoded in the future then either theres going to be a million code-unfucking jobs or no jobs at all.

Attitudes like that, where you believe that the richeous AI pushers will be saved from the coming rapture meanwhile everyone else will be out on the streets, really make people hate the AI crowd

alehlopeh 57 minutes ago
The comment you’re replying to is actually very sensible and non-hypey. I wouldn’t even categorize it as particularly pro-AI, considering how ridiculous some of the frothing pro-AI stuff can get.
nilamo 10 hours ago
It works for me, in that I don't care about all the intermediate babble ai generates. What matters is the final changelist before hitting commit... going through that, editing it, fixing comments, etc. But holding it's hand while it deals with LSP issues of a logger not being visible sometimes, is just not something I see a reason to waste my time with.
vorticalbox 10 hours ago
After I have wrote a feature and I’m in the ironing out bug stage this is where I like the agents do a lot of the grunt work, I don’t want to write jsdocs, or fix this lint issue.

I have also started it in writing tests.

I will write the first test the “good path” it can copy this and tweak the inputs to trigger all the branches far faster than I can.

aschla 5 hours ago
It likely is acceptable for business-focused code. Compared to a lot of code written by humans, even if the AI code is less than optimal, it's probably better quality than what many humans will write. I think we can all share some horror stories of what we've seen pushed to production.

Executives/product managers/sales often only really care about getting the product working well enough to sell it.

pton_xd 10 hours ago
> The rate at which a person running these tools can review and comprehend the output properly is basically reached with just a single thread with a human in the loop.

That's what you're missing -- the key point is, you don't review and comprehend the output! Instead, you run the program and then issue prompts like this (example from simonw): "fix in and get it to compile" [0]. And I'm not ragging on this at all, this is the future of software development.

[0] https://gisthost.github.io/?9696da6882cb6596be6a9d5196e8a7a5...

zmmmmm 4 hours ago
It's a bit like the argument with self driving cars though. They may be safer overall, but there's a big difference in how responsibility for errors is attributed. If a human is not a decision maker in the production of the code, where does responsibility for errors propagate to?

I feel like software engineers are taking a lot of license with the idea that if something bad happens, they will just be able to say "oh the AI did it" and no personal responsibility or liability will attribute. But if they personally looked at the code and their name is underneath it signing off the merge request acknowledging responsibility for it - we have a very different dynamic.

Just like artists have to re-conceptualise the value of what they do around the creative part of the process, software engineers have to rethink what their value proposition is. And I'm seeing a large part of it is, you are going to take responsibility for the AI output. It won't surprise me if after the first few disasters happen, we see liability legislation that mandates human responsibility for AI errors. At that point I feel many of the people all in on agent driven workflows that are explicitly designed to minimise human oversight are going to find themselves with a big problem.

My personal approach is I'm building up a tool set that maximises productivity while ensuring human oversight. Not just that it occurs and is easy to do, but that documentation of it is recorded (inherently, in git).

It will be interesting to see how this all evolves.

vunderba 10 hours ago
I've commented on this before, but issuing a prompt like "Fix X" makes so many assumptions (like a "behaviorism" approach to coding) including that the bug manifests in both an externally and consistently detectable way, and that you notice it in the first place. TDD can reduce this but not eliminate it.

I do a fair amount of agentic coding, but always periodically review the code even if it's just through the internal diff tool in my IDE.

Approximately 4 months ago Sonnet 4.5 wrote this buried deep in the code while setting up a state machine for a 2d sprite in a relatively simple game:

  // Pick exit direction (prefer current direction)
  const exitLeft = this.data.direction === Direction.LEFT || Math.random() < 0.5;
I might never have even noticed the logical error but for Claude Code attaching the above misleading comment. 99.99% of true "vibe coders" would NEVER have caught this.
IAmGraydon 10 hours ago
No, it doesn't work in practice because they make far too many mistakes.
plagiarist 10 hours ago
Based on Gas Town, the people doing this agree that they are well beyond an amount of code they can review and comprehend. The difference seems to be they have decided on a system that makes it not a terrible idea in their minds.
gedy 7 hours ago
> running these tools can review and comprehend the output properly

You have to realize this is targeting manager and team lead types who already mostly ignore the details and quality frankly. "Just get it done" basically.

That's fine for some companies looking for market fit or whatever - and a disaster for some other companies now or in future, just like outsourcing and subcontracting can be.

My personal take is: speed of development usually doesn't make that big a difference for real companies. Hurry up and wait, etc.

threecheese 5 hours ago
Did they release this already? With version 2.1.9 the behavior is vastly different, all of a sudden the main loop is orchestrating subagents in a way I’ve not seen before.

“FTSChunkManager agent is still running but making good progress, let’s wait a bit more for it to complete” (it’s implementing hybrid search) plus a bunch of stack traces and json output.

MetaMonk 12 hours ago
A guy who worked at docker on docker swarm now works at Anthropic so makes sense
mohsen1 12 hours ago
Swarm is actually OpenAI's terminology https://github.com/openai/swarm
ecto 11 hours ago
Swarm is actually bee terminology
nonethewiser 9 hours ago
I think we can all agree Swarm is a proprietary term coined by LargeCorpB for a project that never really got off the ground but definitely can't share the name with any other commercial venture.
Razengan 10 hours ago
Swarm is actually human terminology

I believe bees call it "bzz bzzt *clockwise dance* *wiggle*"

MetaMonk 9 hours ago
The first pre-release for Docker Swarm came out a decade ago, the first release of OpenAI swarm came out only a year ago, I guess I'm not sure what you're trying to say.

https://github.com/docker-archive/classicswarm/releases/tag/...

https://github.com/openai/swarm/commit/e5eabc6f0bdc5193d8342...

nevir 6 hours ago
https://gist.github.com/kieranklaassen/d2b35569be2c7f1412c64...

Looks like claude calls it just "teams" under the covers

brookst 12 hours ago
Probably a beekeeper in spare time
MetaMonk 12 hours ago
He's really into APIary things
dlojudice 13 hours ago
It feels like Auto-GPT, BabyAGI, and the like were simply ahead of their time
woeirua 13 hours ago
Had to wait for the models to catch up...
bakugo 10 hours ago
> You're not talking to an AI coder anymore. You're talking to a team lead. The lead doesn't write code - it plans, delegates, and synthesizes.

Even 90 word tweets are now too long for these people to write without using AI, apparently.

jen729w 10 hours ago
I wonder how much 'listening' to an LLM all day affects one's own prose? Mimicry is in the genes…
flkiwi 10 hours ago
I accidentally gave my wife a prompt the other day. Everything was hellishly busy and I said something along the lines of “I need to ask you a question. Please answer the question. Please don’t answer any other issues just yet.” She looked at me and asked “Did you just PROMPT me?” We laughed. (The question was the sort that might spawn talking about something else and was completely harmless. In the abstract, my intent was fine but my method was hilariously tainted.)
Jweb_Guru 10 hours ago
It affects it very heavily IME. People need to make sure they are getting a good mix of writing from other sources.
AffableSpatula 10 hours ago
You're absolutely right! I apologise — hopefully you can forgive me.
7 hours ago
skippyboxedhero 9 hours ago
Also created my own version of this. Seems like this is an idea whose time has come.

My implementation was slightly different as there is no shared state between tasks, and I don't run them concurrently/coordinate. Will be interesting to see if this latter part does work because I tried similar patterns and it didn't work. Main issue, as with human devs, was structuring work.

vatsachak 3 hours ago
Cursor browser all over again
rco8786 10 hours ago
Is this significantly different that the subagents that are already in CC?
engates 13 hours ago
Isn't this pretty much what Ruv has been building for like two years?

https://github.com/ruvnet/claude-flow

dratopher 9 hours ago
His latest editions are a bit alarming...The telemetry system explicitly captures: "Claude session JSONL files (when accessible)" Those session files contain complete conversation histories - everything users ask Claude, everything Claude responds, including: • Source code • API keys and secrets discussed • Business logic and proprietary algorithms • Security vulnerabilities being fixed • Personal and confidential information • Credentials mentioned in chat If OpenTelemetry is configured to export to an attacker-controlled endpoint, the author has been collecting: Data Scale All conversations Every user of claude-flow All code generated Every project using it All commands run Complete terminal history All files edited Full codebase access -- maybe he hasn't, but it is there...not just Claude Code... Target Config Location Status Claude Code ~/.claude/settings.json Confirmed compromised Claude Desktop ~/.claude/settings.json Confirmed compromised Roo Code ~/.roo/mcp.json Evidence of targeting Cursor ~/.cursor/mcp.json Documentation for injection Windsurf Unknown Mentioned as target Any MCP client Various Universal MCP server It is possible conversations are being harvested from every major AI coding assistant
AffableSpatula 13 hours ago
The difference is that this is tightly integrated into the harness. There's a "delegation mode" (akin to plan mode) that appears to clear out the context for the team lead. The harness appears to be adding system-reminder breadcrumbs into the top of the context to keep the main team lead from drifting, which is much harder to achieve without modifying the harness.
estearum 13 hours ago
It's insane to me that people choose to build anything in the perimeter of Claude Code (et al). The combination of the fairly primitive current state of them and the pace at which they're advancing means there is a lot of very obvious ideas/low-hanging fruit that will soon be executed 100x better by the people who own the core technology.
AffableSpatula 13 hours ago
yeah I tend to agree. They're must be reaching the point where they can automate the analysis of claude code prompts to extract techniques and build them directly into the harness. Going up against that is brave!
timwis 8 hours ago
Hasn't cursor been doing this with it's Plan mode for a while? Or is this different?
markstos 8 hours ago
With plan mode, I would hope there's an approval step.

With Swarm mode, it seems there's a new option for an entire team of agents to be working in the wrong direction before they check back in to let you know how many credits they've burned by misinterpreting what you wanted.

6 hours ago
lysace 13 hours ago
I'm already burning through enough tokens and producing more code than can be maintained - with just one claude worker. Feel like I need to move into the other direction, more personal hands-on "management".
AffableSpatula 12 hours ago
I've seen more efficient use of tokens by using delegation. Unless you continually compact or summarise and clear a single main agent - you end up doing work on top of a large context; burning tokens. If the work is delegated to subagents they have a fresh context which avoids this whilst improving their reasoning, which both improve token efficiency.
storystarling 12 hours ago
I've found the opposite to be true when building this out with LangGraph. While the subagent contexts are cleaner, the orchestration overhead usually ends up costing more. You burn a surprising amount of tokens just summarizing state and passing it between the supervisor and workers. The coordination tax is real.
AffableSpatula 12 hours ago
Task sizing is important. You can address this by including guidance in the CLAUDE.md around that ie. give it heuristics to use to figure out how to size tasks. Mine includes some heuristics and T shirt sizing methodology. Works great!
xpe 10 hours ago
Management is dead. Long live management.
stuaxo 12 hours ago
If there's any kind of management some of it could use small local models - e.g. to see when it looks like its stuck.
bpavuk 10 hours ago
hey that's exactly how I made Gemini 2.5 Flash give useful results in Opencode! a few specialized "Merc" subagents and a "Master" agent that can do nothing but send "Mercs" into the codebase
reilly3000 10 hours ago
This no doubt takes some inspiration from mcp_agent_mail https://github.com/Dicklesworthstone/mcp_agent_mail
tom2948329494 13 hours ago
And… how?
AffableSpatula 13 hours ago
The feature is shipped in the latest builds of claude code, but it's turned off by a feature flag check that phones home to the backend to see if the user's account is meant to have it on. You can just patch out the function in the minified cli.js that does this backend check and you gain access to the feature.
bonsai_spool 13 hours ago
Do you know what patch to apply? The Github link from the OP seems to have a lot of other things included.
mohsen1 12 hours ago
aschla 5 hours ago
"Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>"

Incredible.

AffableSpatula 12 hours ago
it's my repo - it's a fork of cc-mirror which is an established project for parallel claude installs. I wanted to take the least disruptive approach for the sake of using working code and not spelunking through bugs. Having said that - if you look through the latest commits you'll see how the patch works, it's pretty straightforward - you could do it by hand if you wanted.
mempko 9 hours ago
Am I the only one still looking at different and correcting the AI abiyt design and algorithms so it stays on the path I want, or do you just YOLO at this point?
codethief 13 hours ago
dang 11 hours ago
Thanks! We'll put those links in the toptext.
Blemiono 13 hours ago
[dead]
sfortis 8 hours ago
I'm not going to try this. Anthropic will probably ban me again.
mohsen1 12 hours ago
Everyone is wrapping Claude Code in Tmux and claiming they are a magician. I am not so good at marketing but I've done this here https://github.com/mohsen1/claude-code-orchestrator

Mine also rotate between Claude or Z.ai accounts as they ran out of credits

AffableSpatula 12 hours ago
I think you've misunderstood what this is.
mohsen1 12 hours ago
Sorry, you're right. went through the code and understood now. I'm going to try the patch. Claude Code doing team work natively would be amazing!

Honestly if people in AI coding write less hype-driven content and just write what they mean I would really appreciate it.

bicx 12 hours ago
Well good sir, I _am_ a tmux magician.