Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cord: Coordinating Trees of AI Agents

june.kim

Post reply on HN
Print view View original

71–80 of 93 posts

Re: Cord: Coordinating Trees of AI Agents

#71

Post by 4b11b4 »

bizzletk wrote: post #56
AxiomLab wrote: post #49

[dead]

The article addresses this: > This made sense when agents were unreliable. You’d never let GPT-3 decide how to decompose a project. But current models are good at planning. They break problems into subproblems naturally. They understand dependencies. They know when a task is too big for one pass. > So why are we still hardcoding the decomposition?

Sure, decomposition is already in the pre-training corpus. and then we can do some "instruction-tuning" on top. This is fine for the last mile, but that's it. I would consider this unaddressed and after with the root comment.

Re: Cord: Coordinating Trees of AI Agents

#75

Post by mpalmer »

kimjune01 wrote: post #70
mpalmer wrote: post #63

Has the author (not OP) written anything on this topic themselves ? This is a blunt comment, because I am fed up with being asked to read LLM content that the prompter thinks is novel and worthwhile because they don't know better. I can forgive (even root for) someone who puts in the effort themselves to understand a problem and write about it, even if they fall short or miss. They have skin in the game. I have littl…

The criticism about the labeling is valid and I oversold. For clarity, this is what the agent sees: `spawn`: "Create a spawned child node under your node." `fork`: "Create a forked child node (inherits parent context) under your node." The novelty is less about the distinction between the two, it's the tree generation. I would have served you better, if I just left out the parts that aren't critical to the novelty. T…

And thanks for taking the criticism.

In all honesty, "would have written it myself but I was too eager to get it out the door" doesn't really make sense to me. You're acknowledging that you took a shortcut to get it out the door (blog post as tech debt is a new one!) - does that mean you'd like to write something up yourself eventually?

I hope so, and would like to read it. In particular, since this is presented as research, I'd be very interested to read about your experimental observations that show the risks/costs/edge cases/limits of this pattern. As it stands, there's no indication of self-critique or really any process of systematic evaluation of the solution.

Re: Cord: Coordinating Trees of AI Agents

#77

Post by jcheng »

amelius wrote: post #76

Can't the AI just figure out by itself how and when to launch agents?

That’s what this is. It’s just defining two types of subagent relationship (spawned and forked) and providing the minimal MCP API for controlling them. It’s up to the LLMs when and how to use subagents.

Re: Cord: Coordinating Trees of AI Agents

#78

Post by lukan »

amelius wrote: post #76

Can't the AI just figure out by itself how and when to launch agents?

They do. But with fine tuning for your use case you will get more power over what they do and if you do it right (no idea yet, if this tool here will really help) - you will get better results.

Re: Cord: Coordinating Trees of AI Agents

#79

Post by kimjune01 »

mpalmer wrote: post #75
kimjune01 wrote: post #70

Earlier quoted context omitted.

The criticism about the labeling is valid and I oversold. For clarity, this is what the agent sees: `spawn`: "Create a spawned child node under your node." `fork`: "Create a forked child node (inherits parent context) under your node." The novelty is less about the distinction between the two, it's the tree generation. I would have served you better, if I just left out the parts that aren't critical to the novelty. T…

And thanks for taking the criticism. In all honesty, "would have written it myself but I was too eager to get it out the door" doesn't really make sense to me. You're acknowledging that you took a shortcut to get it out the door (blog post as tech debt is a new one!) - does that mean you'd like to write something up yourself eventually? I hope so, and would like to read it. In particular, since this is presented as r…

on Wednesday, I had a dream about agents. Thursday evening, I talked to Claude about trees. That same night, I pushed out the post. There wasn't much rigor involved but yes I will explore more and report back to you!

Re: Cord: Coordinating Trees of AI Agents

#80

Post by tovej »

kimjune01 wrote: post #60
tovej wrote: post #43

This is a vibeslop project with a vibeslop write-up. Trees? Trees aren't expressive enough to capture all dependency structures. You either need directed acyclical graphs or general directed graphs (for iterative problems). Based on the terminology you use, it seems you've conflated the graphs used in task scheduling with trees used in OS process management. The only reason process trees are trees are for OS-specific…

no solution is final, but if you have a better working solution, please share!

DAG-scheduling is a solved issue. If you really need to impement an autonomous LLM agent workflow engine, use a DAG. Just have the LLM declare the edges.

My suggestion is to not do any of that but use a traditional workflow engine / project management tools if you need to boost productivity in processes /projects. You're code quality will improve and your programming skills won't deteriorate. At no cost in productivity.

Post reply on HN