Hacker News
points by bob1029 4 days ago | 0 comments
> I also now reckon with the fatigue of using these agents. Managing 6 different conversations with 6 different robots about 6 different features is overstimulating & exhausting in a way that coding never was.

Anyone using a swarm of agents in November 2026 to write code is no longer at the frontier of capability.

Running multiple system prompts at once is a perfect example of anthropomorphism. We have this fantasy that a community of diversely aligned agents will somehow outperform a single well-aligned agent. There might be some cases where the random walk takes you where you want to go, but how stable and stressful do you want it to be?

Some of us are using AI as a means to make a living now. If I slip even a little bit on best practices my clients will likely turn into ghosts. Multi agent is an extremely expensive form of entertainment in this context. It's the entire basis for why we have these junkies trolling around HN complaining about how they can never get enough tokens. If I was still playing with these ideas in front of my customers I can guarantee I'd be 100% unemployed right now. They brought me in to make AI into a profit center, not a cost center.

[–] framapotari 4 days ago
Can you expand? What is the frontier of capability doing now?
[–] quantiq 4 days ago
The frontier of capability right now is writing most of the code by hand. I'm not joking.

Multiple studies have come out recently that AI use when not used as a tutor leads to loss of learning. It's a great way to ensure you end up jobless in the future when you forget even very basic syntax from no longer having to deal with hard problems. It's why pilots still fly manually by hand even though the autopilot can do practically everything.

[–] senordevnyc 4 days ago
I was curious, found this in their history: https://news.ycombinator.com/item?id=50334030

Being charitable, perhaps they're mostly focused on efficiency, not overall capability. I can see that using swarms probably rarely results in solutions you couldn't reach with a single agent, at much higher cost. I think the tradeoff is that you get to the solution with less clock time though.

That said, the article text they quoted isn't even about swarms, it's just about the mental fatigue of juggling multiple single-agent threads. And there I agree with the article. I keep doing it because of agent speed, maybe I should just bite the bullet and get some $500 subs so I can use Astra ultrafast for everything. Only half joking...

[–] hobofan 4 days ago
I think you skipped over the "about 6 different features" part.

Everything you said only applies to unleashing an agent swarm on a single feature. You are not wrong on your assessment there, but working on multiple features concurrently does come with its own challenges.