Comment by Exoristos
7 hours ago
I don't personally know of any software engineers using AI as "fleets of agents" in a "factory." Sounds like a nightmare.
7 hours ago
I don't personally know of any software engineers using AI as "fleets of agents" in a "factory." Sounds like a nightmare.
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.
> 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.
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".
1 reply →
> 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.
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.
you... don't read hackernews much I take it? This is like 10% of all submissions lately, lol.
In fact I do live outside HN.
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.
Every PR now has auto reviews. That's like at least 3-5+ agents depending on the repo.