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
btables 12 hours ago [-]
Totally. Earth's rotation is a loop too. We should count that.
ratelimitsteve 11 hours ago [-]
rotation and orbit, and technically the eccentricity in the axis as well
monocasa 10 hours ago [-]
There's also at least the galactic orbit. There might be a very large scale orbit as well around the Great Attractor, but the jury's still bery much out on that one.
lioeters 8 hours ago [-]
Kinda getting dizzy thinking about all the loops we're embedded in. Where is the still point in these turning wheels of the world.
fragmede 4 hours ago [-]
Don't forget the Big Bang to the Big Crunch, and then that looping as well.
bicepjai 6 hours ago [-]
I like how you found the pattern of 3 loops. I am working on a similar blog where I had human loop outside the inference loop :) human -> llm-> tool
cheschire 8 hours ago [-]
Anyone have suggestions on implementing loops with a basic $20/mo subscription to claude or gemini? Any blog posts recommended?
gexla 8 hours ago [-]
The article is describing how every harness functions. If you're already using Codex, Claude Code, or Antigravity then you're already doing this. And you get a lot of usage. I generally don't hit my limits with GPT if I stick to reviews of code that cheaper models create. Google gives you a low number of free requests. OpenCode has a generous free tier for open source models (and a plan that is $5 / month for the first month.)
cheschire 6 hours ago [-]
The article describes API calls using code. How does one use these loops in Claude Code (assuming you mean CLI not cloud) or Antigravity (assuming you mean agy not the IDE)?
solumunus 6 hours ago [-]
The article is describing how agents work. You can either read it only to gain that understanding, or read it because you’re trying to build your own version of Claude Code. “How can we use these loops in Claude Code?” doesn’t make any sense.
cheschire 5 hours ago [-]
Oh, interesting.
So am I understanding correctly then that the tools that come with monthly subscriptions are inherently limited and unable to expand to what the article describes in the outermost loops?
solumunus 19 minutes ago [-]
Are you asking if it’s possible to add custom tools to CC/Codex which it can then use? If not, please clarify what you mean.
12 hours ago [-]
philipwhiuk 14 hours ago [-]
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 14 hours ago [-]
I think of them from the outside in, so that's why I illustrated it that way.
NitpickLawyer 11 hours ago [-]
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.
huflungdung 14 hours ago [-]
[dead]
DonHopkins 13 hours ago [-]
You are absolutely correct. It's an i18n/l10n issue. They spin in the opposite direction in the other hemisphere.
Curious how you're addressing this
So am I understanding correctly then that the tools that come with monthly subscriptions are inherently limited and unable to expand to what the article describes in the outermost loops?
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.
See https://www.britannica.com/story/do-toilets-in-different-hem...