Hacker News

points by Exoristos 1 day ago | 0 comments

I don't personally know of any software engineers using AI as "fleets of agents" in a "factory." Sounds like a nightmare.

[–] mywittyname 1 day ago

I usually have a high-level agent drafting plans, then spawning sub-agents to build parts of the plan, other sub-agents to check the work of those agents. Then the PRs have different code review agents looking at the code, on top of the agents for people on my team also reviewing my code.

And I'm probably on the more amateurish end of AI development. As I learned these techniques from YouTube.

When you hear about the work Anthropic researchers are doing, they seem to be using hundreds or thousands of agents to solve problems.

[–] Wheen 1 day ago

> When you hear about the work Anthropic researchers are doing, they seem to be using hundreds or thousands of agents to solve problems.

There's a reason they're Anthropic researchers. The value proposition tanks when you actually have to foot the bill for the tokens you use.

Subagent flows can improve overall performance, but it generally also comes with disproportionately high token use. That gets worse with parallel subagents that are often doing the same things at the same time and cannot share a cache.

[–] mywittyname 1 day ago

So the point I was trying to make is that I'm maybe in the 25th percentile of developers and am using multiple agents for a task, and Anthropic researchers are at the 99th percentile and are using thousands of agents per task.

So the median developer is probably using 5-20 agents at a time for a task. I'm not sure if that crosses the threshold of being a "fleet of agents".

[–] Wheen 1 day ago

I'm curious to see your source for these numbers. Your flow sounds closer to a 99th percentile one than a 25th. I find it hard to believe that a median developer is using 5-20 agents at a time.

[–] NichoPaolucci 1 day ago

Yeah... N=2-3 here but my team prefers having 1 main agent and maybe a couple more finely tuned ones for review / analysis / security... I generally have 2-3 chats going on different tasks but more than that and I lose the plot.

[–] mistrial9 1 day ago

the way I read this passage - author claims to be not a particularly skilled or fast-paced practitioner, and yet it is true that author is using agents like this. Next, very advanced researchers -- in the heart of the AI Frontier industry -- are using many more agents with much larger actions.

The "median developer" refers to the particularly skilled or fast-paced, not that there are continuous numbers of every practitioner using N-agents

[–] _aavaa_ 10 hours ago

Give it another 6 months (if that) and you can drop the cost an order of magnitude.

[–] Exoristos 1 day ago

> And I'm probably on the more amateurish end of AI development. As I learned these techniques from YouTube.

I think that sums up the "fleets of agents" approach fairly well.

[–] tehjoker 1 day ago

They are doing that because they are running into hardware limits with single agents. If one agent made correct decisions and explored spaces efficiently, they would not need hundreds of thousands of agents. It's is the luxury of great wealth that they can produce a large number of possibly defective samples and then select the ones that are not defective.

[–] bigstrat2003 1 day ago

Yeah, I very much dispute the characterization GP made as to how software devs are working. I know some are. But I do not believe it's the majority of people in the field, not by a long shot.

[–] chicagobuss 1 day ago

you... don't read hackernews much I take it? This is like 10% of all submissions lately, lol.

[–] Exoristos 1 day ago

In fact I do live outside HN.

[–] thatsabadlook 14 hours ago

Supposedly they are out there. I heard from one person who claimed it. They didn't have a viable product and said their ai spend was in the tens of thousands a month for over 6 months. 1 employee startup baby

[–] hparadiz 1 day ago

Every PR now has auto reviews. That's like at least 3-5+ agents depending on the repo.