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

LLM Agents Are Simply Graph – Tutorial for Dummies

zacharyhuang.substack.com

Post reply on HN
Print view View original

11–20 of 82 posts

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#11

Post by campbel »

zh2408 wrote: post #8
campbel wrote: post #7

I follow Mr. Huang, read/watch his content and also plan to use PocketFlow in some cases. A preamble, because I don't agree with this assessment. I think agents as nodes in a DAG workflow is _an_ implementation of an agentic system, but is not the systems I most often interact with (e.g. Cursor, Claude + MCP). Agentic systems can be simply the LLM + prompting + tools[1]. LLMs are more than capable (especially chain-o…

Let me clarify: this tutorial focuses on the technical internal implementation of the agent (e.g., OpenAI agent, Pydantic AI, etc.), rather than the UI/UX of the agent-based products that end users interact with.

That's what I am talking about as well. The low-level implementation of an agent isn't necessarily a rigid graph, and I'd actually argue its explicitly not this.

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#12

Post by adamnemecek »

zh2408 wrote: post #10
_pdp_ wrote: post #9

It is hard to put a pin on this one because there are so many thing wrong with this definition. There are agent frameworks that are not rebranded workflow tools too. I don't think this article helps explain anything except putting the intended audience in the same box of mind we were stuck since the invention of programming - i.e. it does not help. Forget about boxes and deterministic control and start thinking of er…

Hey, sorry for the confusion. This tutorial is focusing on the low-level internals of how agents are implemented—much like how intelligent large language models still boil down to matrix multiplications at their core.

Despite the memes, this reductivism is not exactly insightful. Like why stop there? Matrix multiplication is just a bunch of dot product. Which in turn is just cos and magnitude. What insights were generated from this?

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#13

Post by zh2408 »

campbel wrote: post #11
zh2408 wrote: post #8

Earlier quoted context omitted.

Let me clarify: this tutorial focuses on the technical internal implementation of the agent (e.g., OpenAI agent, Pydantic AI, etc.), rather than the UI/UX of the agent-based products that end users interact with.

That's what I am talking about as well. The low-level implementation of an agent isn't necessarily a rigid graph, and I'd actually argue its explicitly not this.

The current implementations of Agents, e.g., OpenAI agents released last week, are based on graph (workflow): https://github.com/openai/openai-agents-python/blob/48ff99bb...

Not sure about Cursor you mentioned as its agent is not open sourced.

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#14

Post by yed »

zh2408 wrote: post #8
campbel wrote: post #7

I follow Mr. Huang, read/watch his content and also plan to use PocketFlow in some cases. A preamble, because I don't agree with this assessment. I think agents as nodes in a DAG workflow is _an_ implementation of an agentic system, but is not the systems I most often interact with (e.g. Cursor, Claude + MCP). Agentic systems can be simply the LLM + prompting + tools[1]. LLMs are more than capable (especially chain-o…

Let me clarify: this tutorial focuses on the technical internal implementation of the agent (e.g., OpenAI agent, Pydantic AI, etc.), rather than the UI/UX of the agent-based products that end users interact with.

The newest generation of agents[0] aren't implemented this way; the model itself is trained to make decisions and a plan of action rather than an explicitly programmed workflow tree.

[0] https://openai.com/index/computer-using-agent/

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#15

Post by ethanwillis »

adamnemecek wrote: post #12
zh2408 wrote: post #10

Earlier quoted context omitted.

Hey, sorry for the confusion. This tutorial is focusing on the low-level internals of how agents are implemented—much like how intelligent large language models still boil down to matrix multiplications at their core.

Despite the memes, this reductivism is not exactly insightful. Like why stop there? Matrix multiplication is just a bunch of dot product. Which in turn is just cos and magnitude. What insights were generated from this?

The reductionism is insightful when it comes to providing an implementation with those specific details in mind.

In the case of LLMs knowing it does boil down to matrix multiplication is insightful and useful because now you know what kind of hardware is best suited to executing a model.

What is actually not insightful or useful is believing LLMs are AGI or conscious.

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#16

Post by zh2408 »

adamnemecek wrote: post #12
zh2408 wrote: post #10

Earlier quoted context omitted.

Hey, sorry for the confusion. This tutorial is focusing on the low-level internals of how agents are implemented—much like how intelligent large language models still boil down to matrix multiplications at their core.

Despite the memes, this reductivism is not exactly insightful. Like why stop there? Matrix multiplication is just a bunch of dot product. Which in turn is just cos and magnitude. What insights were generated from this?

It’s kind of like the different levels of abstraction.

For example, for software projects, the algorithmic level is where most people focus because that’s typically where the biggest optimizations happen. But in some critical scenarios, you have to peel back those layers—down to how the hardware or compiler works—to make the best choices (like picking the right CPU/GPU).

Likewise, with agents, you can work with high-level abstractions for most applications. But if you need to optimize or compare different approaches (tool use vs. MCP vs. prompt-based, for instance), you have to dig deeper into how they’re actually implemented.

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#17

Post by zh2408 »

yed wrote: post #14
zh2408 wrote: post #8

Earlier quoted context omitted.

Let me clarify: this tutorial focuses on the technical internal implementation of the agent (e.g., OpenAI agent, Pydantic AI, etc.), rather than the UI/UX of the agent-based products that end users interact with.

The newest generation of agents[0] aren't implemented this way; the model itself is trained to make decisions and a plan of action rather than an explicitly programmed workflow tree. [0] https://openai.com/index/computer-using-agent/

I think you’re referring to function calling: https://platform.openai.com/docs/guides/function-calling

This still returns a string. You need to explicitly program the branch to the right function. For example, check out how OpenAI Agents, released a week ago, rely on a workflow: https://github.com/openai/openai-agents-python/blob/48ff99bb...

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#18

Post by yed »

zh2408 wrote: post #17
yed wrote: post #14

Earlier quoted context omitted.

The newest generation of agents[0] aren't implemented this way; the model itself is trained to make decisions and a plan of action rather than an explicitly programmed workflow tree. [0] https://openai.com/index/computer-using-agent/

I think you’re referring to function calling: https://platform.openai.com/docs/guides/function-calling This still returns a string. You need to explicitly program the branch to the right function. For example, check out how OpenAI Agents, released a week ago, rely on a workflow: https://github.com/openai/openai-agents-python/blob/48ff99bb...

No I'm referring to the newest generation of agentic models one of which I linked to. These are not fully released but it is where the newest generation of research is headed.

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#20

Post by zh2408 »

yed wrote: post #18
zh2408 wrote: post #17

Earlier quoted context omitted.

I think you’re referring to function calling: https://platform.openai.com/docs/guides/function-calling This still returns a string. You need to explicitly program the branch to the right function. For example, check out how OpenAI Agents, released a week ago, rely on a workflow: https://github.com/openai/openai-agents-python/blob/48ff99bb...

No I'm referring to the newest generation of agentic models one of which I linked to. These are not fully released but it is where the newest generation of research is headed.

It's hard for me to comment on something not open sourced
Post reply on HN