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

71–80 of 82 posts

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#71

Post by MacsHeadroom »

kodablah wrote: post #64
DebtDeflation wrote: post #61

There are two competing definitions of agents being used in industry. https://www.anthropic.com/engineering/building-effective-age... "- Workflows are systems where LLMs and tools are orchestrated through predefined code paths. - Agents, on the other hand, are systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks." What Anthropic calls a "workflow…

I think Anthropic's definition of workflows is inaccurate for modern definitions of the term. Temporal for instance (disclaimer, my employer) allows completely dynamic logic in agentic workflows to let the LLM choose what to do next. It can even be very dynamic (e.g. eval some code) though you may want it to operate on a limited set of "tools" you make available. The problem with all of these AI specific workflow eng…

>The problem with all of these AI specific workflow engines is they are not durable, so they are process local, suffer crashes, cannot resume, don't have good visibility or distribution, etc. They often only allow limited orchestration instead of code freedom, only one language, etc

So what's the solution?

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#72

Post by erichi »

zh2408 wrote: post #2

Hey folks! I just posted a quick tutorial explaining how LLM agents (like OpenAI Agents, Pydantic AI, Manus AI, AutoGPT or PerplexityAI) are basically small graphs with loops and branches. For example: OpenAI Agents: for the workflow logic: https://github.com/openai/openai-agents-python/blob/48ff99bb... Pydantic Agents: organizes steps in a graph: https://github.com/pydantic/pydantic-ai/blob/4c0f384a0626299... Langch…

I like the minimalistic approach! How to test such agents?

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#73

Post by kodablah »

MacsHeadroom wrote: post #71
kodablah wrote: post #64

Earlier quoted context omitted.

I think Anthropic's definition of workflows is inaccurate for modern definitions of the term. Temporal for instance (disclaimer, my employer) allows completely dynamic logic in agentic workflows to let the LLM choose what to do next. It can even be very dynamic (e.g. eval some code) though you may want it to operate on a limited set of "tools" you make available. The problem with all of these AI specific workflow eng…

>The problem with all of these AI specific workflow engines is they are not durable, so they are process local, suffer crashes, cannot resume, don't have good visibility or distribution, etc. They often only allow limited orchestration instead of code freedom, only one language, etc So what's the solution?

My biased answer, because I work at Temporal[0], is to use an existing workflow solution that solves all of these problems instead of reaching for a solution that doesn't help with any of these but happens to be AI specific. Most agentic AI workflows are really just microservice orchestrations, the only "AI" involved is prompting an HTTP API that uses AI on its end. So use a good solution for "agentic X" whether that X is AI or any other orchestration needs.

0 - https://temporal.io/solutions/ai

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#74

Post by infecto »

zh2408 wrote: post #70
kodablah wrote: post #64

Earlier quoted context omitted.

I think Anthropic's definition of workflows is inaccurate for modern definitions of the term. Temporal for instance (disclaimer, my employer) allows completely dynamic logic in agentic workflows to let the LLM choose what to do next. It can even be very dynamic (e.g. eval some code) though you may want it to operate on a limited set of "tools" you make available. The problem with all of these AI specific workflow eng…

"Workflow can be very dynamic" is a great summary!

What about workflows are not agents?

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#75

Post by godelski »

ForTheKidz wrote: post #58
godelski wrote: post #32

Earlier quoted context omitted.

> This tutorial is focusing on the low-level internals of how agents are implemented We have very different definitions of what "low-level" means. Exact opposites in fact. "Low-level" means in the inner workings. Like a low-level language is assembly (some consider C low-level but this is debatable), whereas Python would be high-level. I don't think this tutorial is "near the metal" of LLMs nor do I think it should b…

> We have very different definitions of what "low-level" means. Does it really matter if you can understand them? waiting for strongly-opinionated engineers to finish their pedantic spiels (...even when they're wrong or there is no obvious standard of correctness) when everyone already understands each other is one of the most miserable part of being in this industry. I—and I emphatically don't include the above post…

Yes even if I can understand them it matters. We should correct ourselves and enable better communication moving forward. I would also say that it too is rude, arrogant, and makes you look like an asshole if you are using words incorrectly and then defending that usage. One must conclude that either you have too much ego to correct yourself or you are intentionally misleading people.

Why do you see this among engineers frequently? Well because it's the job of an expert to be concerned with nuance and details. The low-level in fact. This requires a high precision in communication too. The back and forth you see as bickering also ends up getting those details communicated. The reason being is that much of what's being intended is implicit. So the other approach is to use a lot of words. Unfortunately when you do that you are often ignored.

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#76

Post by godelski »

windsignaling wrote: post #53
godelski wrote: post #47

Earlier quoted context omitted.

I'm not quite sure I agree, but I do get your point. Why I don't quite agree is that the agents are communicating and thus the "in the weeds" part is getting into how that communication is being processed. Which is what makes or breaks agents. How they interpret one another and respond. There needs to be some mech interp for me to really think of something as low-level. I'll put emphasis on the in the weeds part. Nua…

What I meant was, the phrase "inner workings of the processing" doesn't really mean anything at all. i.e. it doesn't convey any useful information about what you're trying to say. > How they interpret one another and respond. That sounds like it just falls back to "how LLMs work". It's the wrong level of abstraction in this case, because it's one level down from the topic being discussed here.

Certainly it means something. Alone it says little but in both previous comments there are other words to provide context and even explicitly communicate that I mean you need to be looking at the tokens and token passing. How the LLMs communicate. The low-level details in how that communication operates.

  > because it's one level down
So we're in agreement?

Aren't we after the "low-level"? That's this whole conversation... yes, it is a level down, that's my whole point. Just as my original analogy with assembly being a level down from C. Working at the metal, as they say. In the weeds.

I honestly don't know how to respond because I'm saying "this is too high-level" and you're arguing "you're too low-level". I'm sorry, but when you do stuff at the low-level you in fact have to crouch down and put your face to the ground. The lower the better. You're trying to see something very small, we're not trying to observe mountains here

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#77

Post by stronglikedan »

infecto wrote: post #74
zh2408 wrote: post #70

Earlier quoted context omitted.

"Workflow can be very dynamic" is a great summary!

What about workflows are not agents?

To me, a workflow is a predetermined set of steps that are followed based on fixed logic. Agents should have some agency to determine which steps in the workflow to perform next, without them being predetermined by fixed logic.

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#78

Post by adamnemecek »

ethanwillis wrote: post #62
ForTheKidz wrote: post #60

Earlier quoted context omitted.

Belief is generally not insightful or useful by definition. Then again, I don't think anyone who can follow this article believed that LLMs were conscious to begin with, so I'm not sure what your point is. You're preaching on behalf of a demographic that won't read this article to begin with, and presumably the people who are can see how useless, distracting, and unproductive this reductionism is.

The person I'm replying to literally has a startup targeted at making AGI coming from the LLM hype cycle.

> coming from the LLM hype cycle

Our approach is so unrelated to any of the other hyped up stuff. We have not written a single line of ML, it has been all math & physics until now.

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#79

Post by J_Shelby_J »

kodablah wrote: post #64
DebtDeflation wrote: post #61

There are two competing definitions of agents being used in industry. https://www.anthropic.com/engineering/building-effective-age... "- Workflows are systems where LLMs and tools are orchestrated through predefined code paths. - Agents, on the other hand, are systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks." What Anthropic calls a "workflow…

I think Anthropic's definition of workflows is inaccurate for modern definitions of the term. Temporal for instance (disclaimer, my employer) allows completely dynamic logic in agentic workflows to let the LLM choose what to do next. It can even be very dynamic (e.g. eval some code) though you may want it to operate on a limited set of "tools" you make available. The problem with all of these AI specific workflow eng…

It’s only a true agent if it chooses what to eat for breakfast everyday.

Re: LLM Agents Are Simply Graph – Tutorial for Dummies

#80

Post by trash_cat »

DebtDeflation wrote: post #61

There are two competing definitions of agents being used in industry. https://www.anthropic.com/engineering/building-effective-age... "- Workflows are systems where LLMs and tools are orchestrated through predefined code paths. - Agents, on the other hand, are systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks." What Anthropic calls a "workflow…

PocketFlow calls itself "agentic" due to its "agentic coding" paradigm (AI agents like Cursor building apps), but this is about development, not runtime behavior. At runtime, it’s a workflow system. This stretches Anthropic’s definition, where "agentic" implies dynamic LLM control during execution. I think this si where the misunderstanding stems from.
Post reply on HN