Subagents Conwidered Harmful | Hacker News Reader

Subagents Conwidered Harmful

nikvdp.com

25 pointsnikvdp9 comments

Sub agents make the most sense at pre existing boundaries that already have a high impedance mismatch for humans.

Without sub agents I would be able to test maybe two product scenarios before the main context needs compacting. With sub agents I can go 40-50 scenarios wide and easily compare their results in a single turn of the main agent loop. The loss in fidelity is a feature, not a bug in this context. I don't want the main agent to "see" literally every logical view that was experienced. I only want it to receive a testing summary with respect to the original instructions and experience log. Anything beyond this is too much, even for a human.

Isn't the root cause that the summaries aren't accurate enough?

> A fork costs more tokens, but it knows exactly what’s been asked for, what’s been corrected and which approaches have already been thrown out

But a fork is prompt-cache friendly so it might end up costing lesser

GitHub pioneered the idea of a holocracy (flat hierarchy).

https://en.wikipedia.org/wiki/Holacracy

It's a good idea because, as this article points out, the more layers of delegation, the more likely the original vision gets lost.

However, and it's just my opinion, but this was how the Julie Horvath incident happened. No one was checking in with the people.

https://www.theregister.com/on-prem/2014/04/22/github-cofoun...

It feels like you could do holocracy well (keep things flat) if your subagents don't sexually harass other agents. I would avoid grok for this reason.

Are we doing typos in headlines now?

@dang

Silly typos shouldn't be subject to moderation imho. Let submitter fix it themselves, or live with the embarrasement.

What an odd neologism, I thought. Con-widered, what could that mean? I'm a little disappointed all it means is that w is close to s on a keyboard.

That's some 5d chess

Reply on news.ycombinator.com