Hacker News
The Agentic Loop: Three loops in a trench coat
47 points by btables
ago
|
11 comments
tptacek
|next
[-]
You can always find more loops if you want to write the next version of this post. Anything that runs software is a loop of instruction execution.
swyx
|next
|previous
[-]
there are more than 3: https://www.latent.space/p/loopcraft
jamestimmins
|root
|parent
|next
[-]
The issue I have with loops is that for truly complex work, where I care about building a generalized solution for a complex problem, the agents frequently reward hack and end up burning indefinitely without finishing until I step in.
Curious how you're addressing this
philipwhiuk
|next
|previous
[-]
Aren't the loops the wrong way round in the diagram. The tightest loop is the inference loop, then the tool loop and then human loop?
btables
|root
|parent
|next
[-]
I think of them from the outside in, so that's why I illustrated it that way.
NitpickLawyer
|root
|parent
|next
[-]
Fascinating. I think it's the first time I've heard it put that way.
For me it's more intuitive the other way around, as the "outer" loops increase in complexity (and can have additional separate loops running inside them). It also makes sense because you can always add more (meta) loops that way.